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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mg
    -0.08
    Γ
    -0.07
    isOpen
    -0.07
    261
    -0.07
    ug
    -0.07
     yasal
    -0.06
    126
    -0.06
    258
    -0.06
    CTX
    -0.06
     nás
    -0.06
    POSITIVE LOGITS
     padr
    0.07
     before
    0.07
     thọ
    0.06
     Clair
    0.06
     adulte
    0.06
    �
    0.06
    ูร
    0.06
    Correction
    0.06
    atoire
    0.06
    して
    0.06
    Act Density 0.010%

    No Known Activations