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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ْم
    -0.07
    IPP
    -0.07
    ťan
    -0.06
    サ
    -0.06
    benchmark
    -0.06
    �
    -0.06
    ANTS
    -0.06
    haps
    -0.06
    ูป
    -0.06
     Etsy
    -0.06
    POSITIVE LOGITS
     libertin
    0.07
    ภาษ
    0.06
    reflection
    0.06
     viewpoints
    0.06
     audition
    0.06
     expression
    0.06
     Dynasty
    0.06
    lit
    0.06
     wearing
    0.06
     relaxing
    0.06
    Act Density 0.000%

    No Known Activations