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

    Neuronpedia

    INDEX
    Explanations

    variable declaration ($)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ܗܘ
    2.11
     scones
    2.02
     dáng
    1.97
     skulls
    1.97
     phosphory
    1.95
     FGFR
    1.92
     ακό
    1.91
     asalamualaikum
    1.88
    𝓹
    1.88
     gång
    1.86
    POSITIVE LOGITS
    ت
    2.69
    ik
    2.64
    و
    2.53
    er
    2.42
    ra
    2.36
    ian
    2.34
    erweise
    2.28
    in
    2.27
    يل
    2.22
    mi
    2.08
    Act Density 0.114%

    No Known Activations