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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INI
    -0.07
     bombing
    -0.07
     thrilling
    -0.07
    icine
    -0.06
    YLE
    -0.06
     tons
    -0.06
    olved
    -0.06
    ИТ
    -0.06
    verage
    -0.06
    Tap
    -0.06
    POSITIVE LOGITS
    ;}
↵
    0.07
    CHR
    0.07
    まと
    0.06
    (elem
    0.06
    '}}↵
    0.06
     hashtags
    0.06
    .har
    0.06
     ι
    0.06
     undercover
    0.06
     ذه
    0.06
    Act Density 0.021%

    No Known Activations