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

    Neuronpedia

    INDEX
    Explanations

    counter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nested
    -0.07
    集合
    -0.06
     mpl
    -0.06
     isNew
    -0.06
    isNew
    -0.06
     jedin
    -0.06
     adv
    -0.06
     venda
    -0.06
     shards
    -0.06
     LD
    -0.06
    POSITIVE LOGITS
    -Speed
    0.07
     unders
    0.07
    ск
    0.07
    0.07
    counter
    0.07
    .counter
    0.06
    кор
    0.06
    discord
    0.06
    web
    0.06
    Career
    0.06
    Act Density 0.005%

    No Known Activations