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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rouw
    -0.07
    ğitim
    -0.06
    leşik
    -0.06
    _helpers
    -0.06
     edges
    -0.06
    えば
    -0.06
     Hazard
    -0.06
    だろう
    -0.06
    .accounts
    -0.06
    reiben
    -0.06
    POSITIVE LOGITS
    .pen
    0.07
    шка
    0.07
     台
    0.07
     supervise
    0.06
    score
    0.06
     encoding
    0.06
     SVG
    0.06
    #####↵
    0.06
     SUM
    0.06
     outing
    0.06
    Act Density 0.000%

    No Known Activations