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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Glam
    -0.07
    partial
    -0.07
    риз
    -0.07
    yper
    -0.07
     Heavy
    -0.06
    celain
    -0.06
    IBUT
    -0.06
    rie
    -0.06
     Bru
    -0.06
     уд
    -0.06
    POSITIVE LOGITS
    .promise
    0.06
    $v
    0.06
     vind
    0.06
    _VIDEO
    0.06
     Third
    0.06
    _solver
    0.06
     деся
    0.06
     người
    0.06
     values
    0.06
    ixmap
    0.06
    Act Density 0.010%

    No Known Activations