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

    Neuronpedia

    INDEX
    Explanations

    years like 1582

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    야
    1.40
    욱
    1.40
    ım
    1.38
    ah
    1.27
    oretically
    1.27
    民众
    1.23
    ும்போது
    1.22
    ний
    1.20
    이면
    1.17
    ında
    1.16
    POSITIVE LOGITS
    iť
    1.82
     Noetherian
    1.41
    cutaneous
    1.38
    i
    1.36
    𝓹
    1.34
    type
    1.30
     peroneal
    1.30
     hypersurface
    1.29
    нную
    1.28
    ENAME
    1.27
    Act Density 0.002%

    No Known Activations