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

    Neuronpedia

    INDEX
    Explanations

    warning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surprisingly
    -0.08
     resentment
    -0.08
     sentimental
    -0.08
     favoritos
    -0.08
     aparent
    -0.08
     получается
    -0.08
     получится
    -0.07
     biased
    -0.07
     özg
    -0.07
     bind
    -0.07
    POSITIVE LOGITS
     warnings
    0.11
     advis
    0.11
     issued
    0.11
     घोषणा
    0.11
     waars
    0.11
     advisory
    0.11
     alerts
    0.11
     اعلام
    0.11
    -warning
    0.11
     annon
    0.11
    Act Density 0.022%

    No Known Activations