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

    Neuronpedia

    INDEX
    Explanations

    simplicity/minimalism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     B
    -0.07
    _population
    -0.07
     M
    -0.06
    ');"
    -0.06
     repe
    -0.06
     A
    -0.06
     poz
    -0.06
    ाज
    -0.06
    Money
    -0.06
     např
    -0.06
    POSITIVE LOGITS
    числ
    0.07
    _const
    0.06
    ircuit
    0.06
    itelist
    0.06
    asics
    0.06
    .AutoScaleMode
    0.06
    되고
    0.06
    译
    0.06
    rough
    0.06
     affili
    0.06
    Act Density 0.198%

    No Known Activations