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

    Neuronpedia

    INDEX
    Explanations

    197

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fundra
    -0.07
     kolem
    -0.07
    res
    -0.06
     richtig
    -0.06
    umb
    -0.06
    Decoration
    -0.06
    ấp
    -0.06
     Assets
    -0.06
     nonatomic
    -0.06
     umb
    -0.06
    POSITIVE LOGITS
    197
    0.10
     Prophet
    0.08
     Hindu
    0.07
     اثر
    0.07
     prophet
    0.07
    HAND
    0.07
     Holt
    0.07
    0.07
    Th
    0.07
    ۱۹۷
    0.07
    Act Density 0.013%

    No Known Activations