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

    Neuronpedia

    INDEX
    Explanations

    Addition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    posure
    -0.07
    _d
    -0.07
    stances
    -0.07
     vois
    -0.07
     namely
    -0.06
    ASON
    -0.06
    locked
    -0.06
    _code
    -0.06
    .Project
    -0.06
    票
    -0.06
    POSITIVE LOGITS
     INCLUDING
    0.06
     رئيس
    0.06
     remover
    0.06
    �
    0.06
    =headers
    0.06
     GENERATED
    0.06
     ett
    0.06
     russian
    0.06
    رير
    0.06
     newVal
    0.06
    Act Density 0.083%

    No Known Activations