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

    Neuronpedia

    INDEX
    Explanations

    help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Equivalent
    -0.06
     вред
    -0.06
    arger
    -0.06
    /assets
    -0.06
    .ToolStripMenuItem
    -0.06
    ление
    -0.06
    autiful
    -0.06
     []↵↵↵
    -0.06
     情
    -0.06
    scriptions
    -0.05
    POSITIVE LOGITS
    (ref
    0.07
     GPI
    0.07
    _deriv
    0.07
    .xrTableCell
    0.07
     pastoral
    0.06
    !]
    0.06
     keycode
    0.06
    .keep
    0.06
     jednotliv
    0.06
    Brain
    0.06
    Act Density 0.016%

    No Known Activations