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

    Neuronpedia

    INDEX
    Explanations

    safety features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    变得
    -0.06
    위원
    -0.06
    τού
    -0.06
    irebase
    -0.06
    рас
    -0.06
    	editor
    -0.06
     Depos
    -0.06
    acency
    -0.06
     PARTICULAR
    -0.06
    치를
    -0.06
    POSITIVE LOGITS
    bolt
    0.07
    Diff
    0.06
    .light
    0.06
     cpt
    0.06
     kötü
    0.06
     elekt
    0.06
     extrem
    0.06
     договору
    0.06
    _filled
    0.06
    .SM
    0.06
    Act Density 0.062%

    No Known Activations