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

    Neuronpedia

    INDEX
    Explanations

    user

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proximité
    -0.08
    getter
    -0.07
     jc
    -0.07
    燹
    -0.07
    مواطن
    -0.07
     speed
    -0.07
    .Drawable
    -0.07
    楫
    -0.07
     Identifier
    -0.07
     игров
    -0.07
    POSITIVE LOGITS
     character
    0.07
    _estimate
    0.07
    ירוש
    0.07
    unu
    0.07
    แนะนำ
    0.07
    🎩
    0.07
    ዩ
    0.07
     אתה
    0.06
    ]")↵
    0.06
    again
    0.06
    Act Density 0.039%

    No Known Activations