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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     throwing
    -0.07
    _ix
    -0.07
     Mong
    -0.06
     Marvel
    -0.06
     Colorado
    -0.06
    -hole
    -0.06
    менно
    -0.06
     CAPITAL
    -0.06
     Girls
    -0.06
     ideologies
    -0.06
    POSITIVE LOGITS
    ЙЙ
    0.07
    !',↵
    0.07
     memnun
    0.07
    emmel
    0.07
     XK
    0.07
    가격
    0.06
     عاما
    0.06
    couz
    0.06
    воз
    0.06
    ücret
    0.06
    Act Density 0.079%

    No Known Activations