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

    Neuronpedia

    INDEX
    Explanations

    supposed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EAR
    -0.07
     рай
    -0.07
    +n
    -0.07
    OX
    -0.06
     KM
    -0.06
    _round
    -0.06
    kw
    -0.06
     キ
    -0.06
    IX
    -0.06
    _pattern
    -0.06
    POSITIVE LOGITS
     supposed
    0.14
     supposedly
    0.09
     hợp
    0.07
     Glacier
    0.07
     probable
    0.07
    BODY
    0.07
     japon
    0.07
     suppose
    0.07
    stellen
    0.06
    SUPER
    0.06
    Act Density 0.005%

    No Known Activations