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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -intensive
    -0.08
    specific
    -0.07
    119
    -0.06
    Ｃ
    -0.06
    `).
    -0.06
    initial
    -0.06
     hrs
    -0.06
    서비스
    -0.06
    paused
    -0.06
    39
    -0.06
    POSITIVE LOGITS
    .shortcuts
    0.07
    Dataset
    0.07
    AMB
    0.06
    .opts
    0.06
    .fade
    0.06
     confidently
    0.06
    -navbar
    0.06
    mesi
    0.06
     Clips
    0.06
    ibilities
    0.06
    Act Density 0.021%

    No Known Activations