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

    Neuronpedia

    INDEX
    Explanations

    talking or promised something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ри
    0.53
     молеку
    0.50
    Veget
    0.49
     काग
    0.48
    ].
    0.46
     carnivorous
    0.46
     профессор
    0.45
     paper
    0.45
     CAGR
    0.45
     ganglion
    0.45
    POSITIVE LOGITS
    可能是
    0.49
    ම්
    0.49
    タル
    0.48
    ้
    0.47
    ەڕ
    0.46
     ဆို
    0.46
    羡慕
    0.46
    乃
    0.45
     iesp
    0.45
    валася
    0.44
    Act Density 0.000%

    No Known Activations