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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ladı
    -0.06
    ;left
    -0.06
     З
    -0.06
     lighter
    -0.06
    OLER
    -0.06
     Expedition
    -0.06
    .Route
    -0.06
     myslí
    -0.06
    ++]=
    -0.05
    reak
    -0.05
    POSITIVE LOGITS
     individual
    0.07
    .getDescription
    0.07
     pictures
    0.07
    ège
    0.06
     directing
    0.06
    .source
    0.06
     unidentified
    0.06
    	sh
    0.06
     thankfully
    0.06
     hard
    0.06
    Act Density 0.000%

    No Known Activations