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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ↵↵↵↵↵
    -0.08
    lerden
    -0.06
    iais
    -0.06
     و
    -0.06
    442
    -0.06
     lux
    -0.06
    ream
    -0.06
     projectId
    -0.06
    prom
    -0.06
     inflammation
    -0.06
    POSITIVE LOGITS
     inplace
    0.07
    -MM
    0.06
    _DA
    0.06
    TRY
    0.06
     Comment
    0.06
    .djang
    0.06
    .Schema
    0.06
    _PARAMETERS
    0.06
    �
    0.06
    ListModel
    0.06
    Act Density 0.036%

    No Known Activations