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

    Neuronpedia

    INDEX
    Explanations

    ul

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erhalten
    -0.08
    Vect
    -0.06
    please
    -0.06
    	↵		↵
    -0.06
    phere
    -0.06
     analysed
    -0.06
     gehen
    -0.06
     harmed
    -0.06
     dabei
    -0.06
     Covered
    -0.06
    POSITIVE LOGITS
    .Paint
    0.07
    pipeline
    0.07
    autocomplete
    0.07
     виконав
    0.07
     Τε
    0.06
    otence
    0.06
     insensitive
    0.06
    EDIATE
    0.06
    nem
    0.06
    .visitMethodInsn
    0.06
    Act Density 0.001%

    No Known Activations