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

    Neuronpedia

    INDEX
    Explanations

    share

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wenn
    -0.07
    <Game
    -0.07
     Porter
    -0.07
    .Author
    -0.06
    rokes
    -0.06
    ler
    -0.06
    153
    -0.06
    apor
    -0.06
    -(
    -0.06
    (sd
    -0.06
    POSITIVE LOGITS
     comparatively
    0.06
     Paolo
    0.06
     damages
    0.06
     prohibits
    0.06
    inished
    0.06
    igmatic
    0.06
    bis
    0.06
     behold
    0.06
     شهید
    0.05
     Morrow
    0.05
    Act Density 0.047%

    No Known Activations