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

    Neuronpedia

    INDEX
    Explanations

    specific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pine
    0.18
     Demons
    0.18
     Imm
    0.17
     S
    0.17
     punt
    0.17
     water
    0.17
     Energy
    0.17
     Heart
    0.17
     you
    0.16
     enormous
    0.16
    POSITIVE LOGITS
    从而
    0.26
    进而
    0.19
     emeritus
    0.18
     ومت
    0.18
    的那
    0.17
    模样
    0.17
     públic
    0.17
    而不
    0.17
     (†
    0.17
     élargies
    0.17
    Act Density 0.702%

    No Known Activations