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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     possibile
    -0.08
     col
    -0.08
    Poss
    -0.07
    ucos
    -0.07
     partenaires
    -0.07
    MET
    -0.07
    Sky
    -0.07
    Col
    -0.07
     Extremely
    -0.07
     colossal
    -0.07
    POSITIVE LOGITS
     doek
    0.09
    umsum
    0.08
     વાયર
    0.08
     beer
    0.08
     кред
    0.08
     അട
    0.07
    ريف
    0.07
     carcin
    0.07
    ૂર
    0.07
     plutôt
    0.07
    Act Density 0.098%

    No Known Activations