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

    Neuronpedia

    INDEX
    Explanations

    opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -run
    -0.07
    рем
    -0.06
    .Date
    -0.06
     breakpoint
    -0.06
     isbn
    -0.06
     coercion
    -0.06
    .item
    -0.06
    .When
    -0.06
    .Spec
    -0.06
    .comp
    -0.06
    POSITIVE LOGITS
    _<
    0.07
    ไซ
    0.06
     personalized
    0.06
    地區
    0.06
    JsonProperty
    0.06
     trì
    0.06
     категор
    0.06
    doors
    0.06
    ++)
↵
    0.06
    \">";↵
    0.06
    Act Density 0.030%

    No Known Activations