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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kosher
    -0.07
     passionate
    -0.07
    哪
    -0.06
     wr
    -0.06
     believed
    -0.06
     Airbnb
    -0.05
     kterého
    -0.05
     valuation
    -0.05
    čí
    -0.05
    (tp
    -0.05
    POSITIVE LOGITS
    抵
    0.07
    ｰ
    0.07
    _scores
    0.07
    Hunter
    0.06
     entreprise
    0.06
    AMERA
    0.06
    ْع
    0.06
    zar
    0.06
     Xuân
    0.06
     Liber
    0.06
    Act Density 0.050%

    No Known Activations