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

    Neuronpedia

    INDEX
    Explanations

    names/legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rule
    -0.06
    -reader
    -0.06
    ania
    -0.06
    (old
    -0.06
     Fence
    -0.06
    831
    -0.06
     Shadow
    -0.06
    	old
    -0.06
     qs
    -0.06
     Dante
    -0.06
    POSITIVE LOGITS
     вступ
    0.07
     LAB
    0.07
    İK
    0.07
    ottie
    0.07
    第一
    0.06
    ->{
    0.06
    �i
    0.06
    accom
    0.06
    .stdin
    0.06
     admission
    0.06
    Act Density 0.179%

    No Known Activations