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

    Neuronpedia

    INDEX
    Explanations

    Nature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alnum
    -0.07
    чай
    -0.07
    civil
    -0.06
    .coordinate
    -0.06
     vida
    -0.06
     baja
    -0.06
     مهم
    -0.06
    Russian
    -0.06
     probabil
    -0.06
    #:
    -0.06
    POSITIVE LOGITS
     Nature
    0.22
    Nature
    0.16
     tục
    0.08
    ature
    0.08
    nature
    0.08
    Nat
    0.07
    offee
    0.07
    ATURE
    0.07
    ooth
    0.07
    微
    0.06
    Act Density 0.004%

    No Known Activations