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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Toggle
    -0.07
     Roads
    -0.07
     DISABLE
    -0.07
    -ro
    -0.07
     دان
    -0.06
    �
    -0.06
    Ranges
    -0.06
    Tiny
    -0.06
    _UPDATED
    -0.06
     قطع
    -0.06
    POSITIVE LOGITS
     após
    0.07
     avec
    0.06
    افظ
    0.06
    igua
    0.06
     thems
    0.06
     Kasım
    0.06
    ounter
    0.06
    웨디시
    0.06
     coveted
    0.06
    ję
    0.06
    Act Density 0.068%

    No Known Activations