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

    Neuronpedia

    INDEX
    Explanations

    asking what is/are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    0.32
    *
    0.31
    _",
    0.30
    기
    0.29
    **
    0.28
    在她
    0.28
    ్రు
    0.27
    و
    0.26
    νε
    0.26
    ეც
    0.26
    POSITIVE LOGITS
     it
    0.72
     the
    0.71
     this
    0.58
     यह
    0.58
     they
    0.57
     you
    0.54
     he
    0.51
    the
    0.50
     это
    0.50
     there
    0.49
    Act Density 0.185%

    No Known Activations