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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     först
    -0.08
    pricing
    -0.08
    _TARGET
    -0.08
     पैसे
    -0.07
     opportunity
    -0.07
     upgrades
    -0.07
     initiatives
    -0.07
     proactive
    -0.07
    Stone
    -0.07
    _validation
    -0.07
    POSITIVE LOGITS
     acos
    0.14
     atan
    0.11
     trigo
    0.10
     unary
    0.10
     Popular
    0.09
     sqrt
    0.09
    Builtin
    0.09
    -ln
    0.09
     Mathemat
    0.09
    χαν
    0.09
    Act Density 0.010%

    No Known Activations