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

    Neuronpedia

    INDEX
    Explanations

    common english words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     protobuf
    -0.07
    /pm
    -0.06
    doing
    -0.06
    /vector
    -0.06
     wine
    -0.06
     Calculator
    -0.06
    きな
    -0.06
    XM
    -0.06
    _redirected
    -0.06
    umed
    -0.06
    POSITIVE LOGITS
     Tas
    0.06
    �
    0.06
    LOSS
    0.06
    -binary
    0.06
    檢
    0.06
     �
    0.06
    _angle
    0.06
     ─
    0.06
    .Boolean
    0.06
     quiero
    0.06
    Act Density 0.232%

    No Known Activations