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

    Neuronpedia

    INDEX
    Explanations

    This or The

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ومن
    1.42
    wellery
    1.32
    και
    1.28
    芰
    1.18
    াক
    1.17
    avate
    1.13
    穸
    1.13
     pathogenesis
    1.13
    ization
    1.12
    ../../
    1.11
    POSITIVE LOGITS
     This
    1.70
     The
    1.61
    This
    1.46
    The
    1.44
     هذا
    1.41
    it
    1.38
     You
    1.38
    ↵
    1.36
    d
    1.36
     That
    1.35
    Act Density 0.003%

    No Known Activations