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

    Neuronpedia

    INDEX
    Explanations

    has have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    frac
    -0.07
    زار
    -0.07
     Martin
    -0.06
     chicas
    -0.06
     CALC
    -0.06
     Physics
    -0.06
    Can
    -0.06
     Could
    -0.06
    ilate
    -0.06
     Pressure
    -0.06
    POSITIVE LOGITS
    Cascade
    0.07
    ProgressHUD
    0.06
     Raises
    0.06
    -е
    0.06
     Moines
    0.06
     intense
    0.06
    하시
    0.06
     TIM
    0.06
     vc
    0.06
    AVED
    0.06
    Act Density 0.233%

    No Known Activations