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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     куп
    -0.07
    Representation
    -0.07
     Hoy
    -0.06
     maintaining
    -0.06
     whisk
    -0.06
     Adventures
    -0.06
    kud
    -0.06
     demek
    -0.06
     believed
    -0.06
     RULE
    -0.06
    POSITIVE LOGITS
    션
    0.07
     WordPress
    0.06
     bude
    0.06
    ël
    0.06
    _emlrt
    0.06
    رح
    0.06
    StateToProps
    0.06
     celé
    0.06
    �n
    0.06
    izabeth
    0.06
    Act Density 0.054%

    No Known Activations