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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ΟΛΟΓ
    -0.07
    .assignment
    -0.07
    ে
    -0.06
    Po
    -0.06
    @↵↵
    -0.06
     واحدة
    -0.06
    zcze
    -0.06
    тех
    -0.06
    Ber
    -0.06
    -clean
    -0.06
    POSITIVE LOGITS
     Моск
    0.06
    -host
    0.06
    フ�
    0.06
     scenic
    0.06
    .zoom
    0.06
    .userData
    0.06
     Jaime
    0.05
     hilarious
    0.05
    ıf
    0.05
    ENCIES
    0.05
    Act Density 0.007%

    No Known Activations