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

    Neuronpedia

    INDEX
    Explanations

    fx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consequence
    -0.08
    _imp
    -0.07
    .Tx
    -0.07
     irreversible
    -0.07
     buried
    -0.07
     consequences
    -0.07
    ști
    -0.07
     દેખ
    -0.07
     scandals
    -0.07
    اؤ
    -0.07
    POSITIVE LOGITS
     groceries
    0.09
     свеж
    0.09
     metropolitan
    0.09
    分快
    0.08
     greens
    0.08
     Bloomington
    0.08
     cuenta
    0.08
     comptes
    0.08
    атков
    0.08
     cuentas
    0.08
    Act Density 0.004%

    No Known Activations