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

    Neuronpedia

    INDEX
    Explanations

    specifying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    탄소년단
    0.43
    悧
    0.43
    Assumption
    0.43
    Existence
    0.43
    Whoever
    0.41
    Elena
    0.41
     Anybody
    0.40
     наші
    0.40
    Anybody
    0.40
    আমাদের
    0.39
    POSITIVE LOGITS
     specifying
    1.65
     specify
    1.55
     specified
    1.48
     specifies
    1.48
     Specify
    1.43
    指定
    1.41
    specify
    1.35
    を指定
    1.35
    Specify
    1.34
     especificar
    1.30
    Act Density 0.039%

    No Known Activations