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

    Neuronpedia

    INDEX
    Explanations

    random, quantum, squares, connector

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SY
    0.40
     HSC
    0.40
     Twain
    0.38
     Egan
    0.36
     Bial
    0.36
     examiners
    0.36
     HCC
    0.36
     faintly
    0.36
     blushing
    0.36
     lottery
    0.36
    POSITIVE LOGITS
    aturing
    0.40
    ної
    0.40
    Mesh
    0.39
     复
    0.38
    ability
    0.37
     привле
    0.37
    力和
    0.36
    Sent
    0.36
    ומי
    0.36
    NPC
    0.35
    Act Density 0.000%

    No Known Activations