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

    Neuronpedia

    INDEX
    Explanations

    param

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    糖
    -0.07
    .Arrays
    -0.07
    dependency
    -0.07
     thừa
    -0.06
    alog
    -0.06
    apel
    -0.06
    Que
    -0.06
     breadth
    -0.06
    мир
    -0.06
     bam
    -0.06
    POSITIVE LOGITS
    (completion
    0.07
    .signals
    0.07
     дир
    0.06
    (False
    0.06
    .Formatter
    0.06
    ・・・
    0.06
    (per
    0.06
    Reuse
    0.06
    一切
    0.06
    aepernick
    0.06
    Act Density 0.005%

    No Known Activations