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

    Neuronpedia

    INDEX
    Explanations

    this is a adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    意思
    1.02
     intermedia
    0.96
    ს
    0.95
    auche
    0.94
    სა
    0.94
    cribing
    0.90
    ামের
    0.90
    vred
    0.89
     Technol
    0.88
    股
    0.87
    POSITIVE LOGITS
    ות
    1.90
    ри
    1.73
    ור
    1.52
    ли
    1.46
     festgestellt
    1.35
    ة
    1.33
    ർ
    1.32
    or
    1.31
    as
    1.30
    es
    1.29
    Act Density 0.338%

    No Known Activations