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

    Neuronpedia

    INDEX
    Explanations

    reproduce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avid
    -0.07
    .linalg
    -0.07
    เวลา
    -0.07
     greeting
    -0.07
    controlled
    -0.07
     formul
    -0.06
     assign
    -0.06
    izi
    -0.06
     flexDirection
    -0.06
    發展
    -0.06
    POSITIVE LOGITS
    _FA
    0.09
     moth
    0.08
    揿
    0.07
    鲴
    0.07
     Bethesda
    0.07
    TRACE
    0.07
    香菇
    0.07
    数控
    0.07
    ٫
    0.07
    鸭
    0.07
    Act Density 0.001%

    No Known Activations