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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     no
    -1.01
    no
    -0.95
    No
    -0.83
     No
    -0.67
    NO
    -0.67
    .
    -0.66
     NO
    -0.64
     ändå
    -0.58
    IntoConstraints
    -0.58
     poussière
    -0.57
    POSITIVE LOGITS
     indication
    0.66
     immediate
    0.64
     semblance
    0.64
     shortage
    0.63
     difference
    0.62
     guarantee
    0.62
     expectation
    0.62
     outward
    0.62
     choice
    0.62
     appearance
    0.62
    Act Density 0.048%

    No Known Activations