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

    Neuronpedia

    INDEX
    Explanations

    rights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     níž
    -0.07
     مایل
    -0.07
     marginRight
    -0.06
    เย
    -0.06
     παιδ
    -0.06
     Salvation
    -0.06
     дет
    -0.06
     مثال
    -0.06
    leitung
    -0.06
    .$.
    -0.06
    POSITIVE LOGITS
     ISO
    0.07
    .Are
    0.06
     PROCESS
    0.06
    _bb
    0.06
     prav
    0.06
    _less
    0.06
    认为
    0.06
     Batch
    0.06
     доп
    0.06
    刚
    0.06
    Act Density 0.000%

    No Known Activations