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

    Neuronpedia

    INDEX
    Explanations

    can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.82
    Ability
    0.72
    能夠
    0.71
    क
    0.71
    ά
    0.70
    IK
    0.70
    İ
    0.70
     יכול
    0.69
    ে
    0.69
    IGNED
    0.68
    POSITIVE LOGITS
     cualquiera
    1.05
     this
    0.94
     any
    0.89
     optar
    0.88
     هذا
    0.88
     dowol
    0.86
     aplicar
    0.83
     alternatively
    0.83
     aussi
    0.81
    opies
    0.81
    Act Density 0.038%

    No Known Activations