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

    Neuronpedia

    INDEX
    Explanations

    code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     разви
    -0.06
    Highlighted
    -0.06
    Tek
    -0.06
    _COOKIE
    -0.06
    -feature
    -0.06
    unbind
    -0.06
    .Platform
    -0.06
    .modules
    -0.06
     мыш
    -0.06
     Unsure
    -0.05
    POSITIVE LOGITS
     unmistak
    0.08
    ula
    0.07
    "How
    0.07
     treason
    0.07
     Erica
    0.06
    Danger
    0.06
     eighty
    0.06
    spd
    0.06
    adden
    0.06
    usch
    0.06
    Act Density 0.279%

    No Known Activations