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

    Neuronpedia

    INDEX
    Explanations

    cause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pus
    -0.06
     touchdown
    -0.06
     smoker
    -0.06
    >Last
    -0.06
     grave
    -0.06
     slun
    -0.06
    068
    -0.06
    —all
    -0.06
    .slide
    -0.06
    :type
    -0.06
    POSITIVE LOGITS
    電子
    0.08
    ظام
    0.07
    uien
    0.06
    .success
    0.06
    crire
    0.06
     Salmon
    0.06
    ENTE
    0.06
    بعد
    0.06
    (outfile
    0.06
    小时
    0.06
    Act Density 0.000%

    No Known Activations