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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forgotten
    -0.07
     ("\
    -0.06
    namespace
    -0.06
    apro
    -0.06
    ふ
    -0.06
     leur
    -0.06
    bundles
    -0.06
     parody
    -0.06
     bundled
    -0.06
     rovněž
    -0.06
    POSITIVE LOGITS
     Amit
    0.08
    _HOST
    0.07
     gens
    0.07
     flute
    0.07
     Encyclopedia
    0.06
     �
    0.06
    .UserInfo
    0.06
    (samples
    0.06
    	LOG
    0.06
     números
    0.06
    Act Density 0.000%

    No Known Activations