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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or subjects in relation to their effect or significance

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

    make them suitable/ideal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.68
    WaitGroup
    -0.55
    BagConstraints
    -0.49
    PerformLayout
    -0.48
     esternos
    -0.48
    GEBURTSDATUM
    -0.47
     Taktlose
    -0.47
     خارجية
    -0.46
     baum
    -0.45
    ╼
    -0.45
    POSITIVE LOGITS
     unique
    0.74
     uniquely
    0.72
     wyjątk
    0.71
     particularly
    0.68
     unsuitable
    0.62
     attractive
    0.59
     suitable
    0.58
     bijzonder
    0.58
    unique
    0.57
     worthy
    0.57
    Act Density 0.024%

    No Known Activations