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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ":{↵
    -0.08
     保
    -0.08
    ਾਡੇ
    -0.08
     जैसे
    -0.08
    ਾਨੂੰ
    -0.08
     편
    -0.08
     бли
    -0.07
     చివ
    -0.07
     utmost
    -0.07
     جیسے
    -0.07
    POSITIVE LOGITS
    ًا
    0.09
    اً
    0.08
     בנושא
    0.07
     trek
    0.07
     individual
    0.07
     halinde
    0.07
     salari
    0.07
    .Connection
    0.07
     costing
    0.07
     individuais
    0.07
    Act Density 0.036%

    No Known Activations