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

    Neuronpedia

    INDEX
    Explanations

    Code and non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (JS
    -0.09
     violent
    -0.08
     �
    -0.08
     eros
    -0.08
    (Gravity
    -0.08
     वर्षीय
    -0.08
    violent
    -0.08
    óvel
    -0.08
     나
    -0.07
    @gmail
    -0.07
    POSITIVE LOGITS
     retired
    0.08
    Ret
    0.08
    .ret
    0.08
     retina
    0.07
    -ret
    0.07
     Publ
    0.07
     Stock
    0.07
    _WEIGHT
    0.07
    _ret
    0.07
     theatre
    0.07
    Act Density 0.006%

    No Known Activations