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

    Neuronpedia

    INDEX
    Explanations

    thoughts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ledge
    -0.07
    atchet
    -0.06
    ек
    -0.06
    INGTON
    -0.06
    _PRESS
    -0.06
    깢
    -0.06
     reduce
    -0.06
    ()).
    -0.06
    stration
    -0.06
    olson
    -0.06
    POSITIVE LOGITS
    LineStyle
    0.07
    -NLS
    0.07
    显露
    0.07
    彟
    0.07
     unset
    0.07
    萦
    0.07
    .Transform
    0.07
    กระบวน
    0.07
    浉
    0.07
     sluts
    0.07
    Act Density 0.068%

    No Known Activations