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

    Neuronpedia

    INDEX
    Explanations

    creating or providing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    神经
    0.27
    时间
    0.27
    스러운
    0.26
    临
    0.26
    ﻟ
    0.26
    合适的
    0.25
    ecção
    0.25
    らの
    0.25
    ہم
    0.25
    мся
    0.25
    POSITIVE LOGITS
     creates
    0.39
     gave
    0.32
     provide
    0.31
     gives
    0.31
     maintains
    0.30
    rives
    0.30
     provides
    0.30
    took
    0.29
     brings
    0.29
     allows
    0.29
    Act Density 0.160%

    No Known Activations