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

    Neuronpedia

    INDEX
    Explanations

    days

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    essions
    -0.08
    gesehen
    -0.08
    dens
    -0.07
    ólnie
    -0.07
    amilton
    -0.07
     آن
    -0.07
    oom
    -0.07
    REFIX
    -0.07
    einander
    -0.07
     visibility
    -0.07
    POSITIVE LOGITS
     Debt
    0.09
     Signed
    0.09
     signed
    0.09
     overseas
    0.09
    Fiscal
    0.09
    _signed
    0.09
    (email
    0.08
    Signed
    0.08
    政策
    0.08
    Unsigned
    0.08
    Act Density 0.005%

    No Known Activations