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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions and their modalities, particularly in relation to necessity and capability

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

    before Japanese and Romance language suffixes

    np_acts-logits-general · gemini-2.0-flash

    verbs in various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.78
    HasAnnotation
    -0.65
     Jefus
    -0.65
     Monfieur
    -0.64
     Hift
    -0.60
     Majefty
    -0.60
    сторія
    -0.59
     Houſe
    -0.59
    ítez
    -0.58
    QMetaType
    -0.58
    POSITIVE LOGITS
    ме
    0.58
    Skocz
    0.53
    Rüyada
    0.52
     vallen
    0.51
     relev
    0.50
     memer
    0.49
    }}}$
    0.49
     {};
    0.49
     {};
    0.48
    lah
    0.47
    Act Density 0.046%

    No Known Activations