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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xes
    -0.07
    ्पत
    -0.07
     �
    -0.07
    ίθ
    -0.07
    /views
    -0.07
    -driving
    -0.07
    .results
    -0.07
    _saved
    -0.06
     Bennett
    -0.06
     scarce
    -0.06
    POSITIVE LOGITS
    -human
    0.08
    ([('
    0.07
    cstdlib
    0.07
    :";↵
    0.06
    释
    0.06
    继
    0.06
     ژانویه
    0.06
     Franc
    0.06
     Coupe
    0.06
     rasp
    0.06
    Act Density 0.000%

    No Known Activations