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

    Neuronpedia

    INDEX
    Explanations

    Age of Exploration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     menjadi
    -0.08
     становится
    -0.08
    [type
    -0.08
     стало
    -0.08
    成为
    -0.08
     مرت
    -0.08
     becomes
    -0.07
     becoming
    -0.07
     коррект
    -0.07
     إجراءات
    -0.07
    POSITIVE LOGITS
     theories
    0.08
     locate
    0.08
     industri
    0.08
     pigments
    0.08
     scientifically
    0.08
    appable
    0.07
     brag
    0.07
     glory
    0.07
     doctrines
    0.07
     prestige
    0.07
    Act Density 0.005%

    No Known Activations