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
    -view
    -0.07
     relentlessly
    -0.07
     Epid
    -0.07
    -spe
    -0.06
    ildi
    -0.06
     mutation
    -0.06
    _photos
    -0.06
     торгів
    -0.06
     investigators
    -0.06
     Romantic
    -0.06
    POSITIVE LOGITS
     mia
    0.07
     Norman
    0.07
    (EFFECT
    0.06
    'ın
    0.06
    SEC
    0.06
    isson
    0.06
    =X
    0.06
    #[
    0.06
     mét
    0.06
    -INF
    0.06
    Act Density 0.044%

    No Known Activations