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

    Neuronpedia

    INDEX
    Explanations

    Math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _permissions
    -0.07
    ixel
    -0.06
    _row
    -0.06
    fort
    -0.06
    _mass
    -0.06
    ocide
    -0.06
    nerRadius
    -0.06
    ycles
    -0.06
     bitcoin
    -0.06
    .Remove
    -0.06
    POSITIVE LOGITS
    ὴ
    0.07
    י
    0.07
     죽
    0.06
    WS
    0.06
     postup
    0.06
    яем
    0.06
    软雅黑
    0.06
     cs
    0.06
    ainer
    0.06
     Burn
    0.06
    Act Density 0.127%

    No Known Activations