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
     Egypt
    -0.07
    umlu
    -0.07
     bacteria
    -0.07
    .batch
    -0.07
    /pi
    -0.07
     Division
    -0.07
    obs
    -0.07
     congest
    -0.06
     Irvine
    -0.06
    _win
    -0.06
    POSITIVE LOGITS
     �
    0.08
    เธ
    0.06
     sábado
    0.06
    ρε
    0.06
     πρα
    0.06
    _WITH
    0.06
    radouro
    0.06
    faf
    0.06
     plagiar
    0.06
     mysl
    0.06
    Act Density 0.181%

    No Known Activations