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

    Neuronpedia

    INDEX
    Explanations

    Car reviews and features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chanting
    -0.07
    альных
    -0.07
    ADING
    -0.07
     bowling
    -0.07
    .find
    -0.06
    arsed
    -0.06
    "${
    -0.06
     wrestler
    -0.06
     skulle
    -0.06
    LAN
    -0.06
    POSITIVE LOGITS
     Claude
    0.06
     Neu
    0.06
    ActivityIndicator
    0.06
     Instituto
    0.06
    改革
    0.06
     jsx
    0.05
     другого
    0.05
    海外
    0.05
     Neil
    0.05
     dealloc
    0.05
    Act Density 0.162%

    No Known Activations