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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TypeDef
    -0.08
    یف
    -0.07
     元
    -0.07
    _floor
    -0.07
    .Sc
    -0.06
    Дж
    -0.06
    े.
    -0.06
    javascript
    -0.06
    供应
    -0.06
     Assange
    -0.06
    POSITIVE LOGITS
    fine
    0.07
    _hover
    0.06
    rang
    0.06
     vztah
    0.06
    esteem
    0.06
    kat
    0.06
     Thank
    0.06
    .MOUSE
    0.05
     catalog
    0.05
     approach
    0.05
    Act Density 0.010%

    No Known Activations