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

    Neuronpedia

    INDEX
    Explanations

    Obviously

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    或
    -0.07
     rush
    -0.07
    arser
    -0.07
     reforms
    -0.07
     strat
    -0.06
     ard
    -0.06
    dete
    -0.06
    Por
    -0.06
    発売
    -0.06
    را
    -0.06
    POSITIVE LOGITS
     Obviously
    0.12
    Obviously
    0.11
     obviously
    0.09
    FOX
    0.07
    smarty
    0.07
    viously
    0.07
     Něm
    0.07
    Clearly
    0.06
     Eb
    0.06
    ochrome
    0.06
    Act Density 0.006%

    No Known Activations