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

    Neuronpedia

    INDEX
    Explanations

    aff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oret
    -0.07
    ustralia
    -0.06
    äche
    -0.06
    early
    -0.06
    `=
    -0.06
    _options
    -0.06
    >m
    -0.06
     Jul
    -0.06
    nutrition
    -0.06
    arge
    -0.06
    POSITIVE LOGITS
    /ad
    0.08
     aff
    0.07
    AFF
    0.07
     fills
    0.06
     firm
    0.06
    signature
    0.06
    Aff
    0.06
     aph
    0.06
    TH
    0.06
    -aff
    0.06
    Act Density 0.014%

    No Known Activations