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
    cly
    -0.08
    му
    -0.06
     составляет
    -0.06
    .An
    -0.06
     Thánh
    -0.06
    -wife
    -0.06
    ifers
    -0.06
    .design
    -0.06
    那里
    -0.06
    Resume
    -0.06
    POSITIVE LOGITS
     ElseIf
    0.07
     initializer
    0.06
    _not
    0.06
    养
    0.06
    erosis
    0.06
    (()=>
    0.06
    _thumbnail
    0.06
    (acc
    0.06
    indsight
    0.06
    ρών
    0.06
    Act Density 0.000%

    No Known Activations