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

    Neuronpedia

    INDEX
    Explanations

    .prototype

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -js
    -0.07
    Giving
    -0.07
     ◄
    -0.07
     아�
    -0.06
     Riv
    -0.06
    анси
    -0.06
    _js
    -0.06
     ↓
    -0.06
    vw
    -0.06
    -",
    -0.06
    POSITIVE LOGITS
    .Claims
    0.07
    Summary
    0.06
     pale
    0.06
    .prototype
    0.06
     �
    0.06
     virtue
    0.06
     conform
    0.06
    GRP
    0.06
    _PROC
    0.06
     climbing
    0.06
    Act Density 0.001%

    No Known Activations