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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [keys
    -0.08
     foresee
    -0.07
    𝜙
    -0.06
    喏
    -0.06
    響
    -0.06
    蜾
    -0.06
     Taco
    -0.06
    annes
    -0.06
    λ
    -0.06
     Led
    -0.06
    POSITIVE LOGITS
     처
    0.07
     shouldn
    0.07
    Paren
    0.07
    步
    0.06
    ינג
    0.06
     GER
    0.06
    مصل
    0.06
     проц
    0.06
    招聘会
    0.06
    ህ
    0.06
    Act Density 0.000%

    No Known Activations