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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ülen
    -0.06
    ieron
    -0.06
    shoot
    -0.06
    weeney
    -0.06
     nominees
    -0.06
    speed
    -0.06
     万
    -0.06
    atories
    -0.06
     disciple
    -0.06
    belum
    -0.06
    POSITIVE LOGITS
    ानव
    0.08
     Morav
    0.07
    _im
    0.07
    ")));
    0.07
    <<<<
    0.06
    .hasOwnProperty
    0.06
    часно
    0.06
    epoch
    0.06
    )throws
    0.06
    _PRIV
    0.06
    Act Density 0.005%

    No Known Activations