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

    Neuronpedia

    INDEX
    Explanations

    scientific screening/selection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _args
    -0.08
    $args
    -0.08
     γνώ
    -0.07
     anlat
    -0.07
    araan
    -0.07
    ,arg
    -0.07
    敬
    -0.07
     Verlet
    -0.07
     gratuito
    -0.07
    :///
    -0.07
    POSITIVE LOGITS
     candidates
    0.12
     Candidates
    0.12
     ઉમેદ
    0.11
     candidate
    0.11
    candidate
    0.10
    (candidate
    0.10
    Candidates
    0.10
    _candidates
    0.10
     kandid
    0.10
    Candidate
    0.10
    Act Density 0.005%

    No Known Activations