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

    Neuronpedia

    INDEX
    Explanations

    #include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hack
    -0.07
     Tong
    -0.07
     mír
    -0.07
    ayne
    -0.07
     vectors
    -0.07
    gement
    -0.07
    attery
    -0.07
    ips
    -0.06
     Prep
    -0.06
    radio
    -0.06
    POSITIVE LOGITS
     Scotch
    0.06
     Disable
    0.06
    мель
    0.06
    .timeout
    0.06
    .↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     бач
    0.06
     Millennials
    0.06
    Analyzer
    0.06
     debido
    0.06
    /remove
    0.06
    Act Density 0.009%

    No Known Activations