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

    Neuronpedia

    INDEX
    Explanations

    vir

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tru
    -0.07
     city
    -0.07
     Explain
    -0.06
     actionTypes
    -0.06
     BOTH
    -0.06
     basit
    -0.06
     Arap
    -0.06
    ULE
    -0.06
    getObject
    -0.06
    _pay
    -0.06
    POSITIVE LOGITS
     陈
    0.07
    eptal
    0.07
     Fen
    0.06
    :i
    0.06
     despair
    0.06
    ového
    0.06
    弟
    0.06
    }@
    0.06
     arousal
    0.06
    “,
    0.06
    Act Density 0.017%

    No Known Activations