Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    policies or characteristics related to rules and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Verbs "is", "was", "are", and "be"

    np_acts-logits-general · gemini-2.0-flash

    forms of "to be" followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jLabel
    -0.31
    CP
    -0.31
    EnableWeb
    -0.30
     OnEnable
    -0.29
    optionalTypeArgs
    -0.27
     onResume
    -0.26
    unhofer
    -0.26
    fpm
    -0.26
    onShow
    -0.26
    cp
    -0.25
    POSITIVE LOGITS
    majánló
    0.78
    Sucesor
    0.61
    either
    0.60
    ConstraintMaker
    0.59
     Geſch
    0.59
     consists
    0.58
     незавершена
    0.57
     Waſſer
    0.56
     consisted
    0.56
     témoig
    0.56
    Act Density 0.673%

    No Known Activations