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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ければ
    -0.08
    →→
    -0.07
    การจ
    -0.07
     enerji
    -0.07
    ありがとう
    -0.07
    iyle
    -0.06
    uridad
    -0.06
     plung
    -0.06
    ンク
    -0.06
     Warwick
    -0.06
    POSITIVE LOGITS
    -num
    0.07
     Automobile
    0.06
     dah
    0.06
    ighbor
    0.06
    _cookie
    0.06
     rumors
    0.06
     cosmetic
    0.06
    )");↵
    0.06
    :nil
    0.06
    .KEY
    0.06
    Act Density 0.010%

    No Known Activations