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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     turist
    -0.07
    qe
    -0.07
     eso
    -0.07
    ijo
    -0.06
     multiplic
    -0.06
     Retro
    -0.06
     retro
    -0.06
    .PLAIN
    -0.06
    >,</
    -0.06
    ortic
    -0.06
    POSITIVE LOGITS
    ریز
    0.07
    existing
    0.07
    hammad
    0.06
    hesive
    0.06
    Compiled
    0.06
    ................
    0.06
    _TOPIC
    0.06
     dlg
    0.06
     регули
    0.06
    changed
    0.06
    Act Density 0.015%

    No Known Activations