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

    Neuronpedia

    INDEX
    Explanations

    AI auditing and binary models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lack
    0.44
     തൊഴിലാ
    0.41
     吸
    0.41
     หล
    0.40
    don
    0.39
    λον
    0.39
    squig
    0.39
     പ്രതിഷേധ
    0.39
     domést
    0.39
    ❁
    0.39
    POSITIVE LOGITS
    aline
    0.46
     bonds
    0.41
     seats
    0.39
     social
    0.39
     مارچ
    0.39
     centre
    0.39
     deposits
    0.39
     library
    0.38
     BIN
    0.38
     απε
    0.38
    Act Density 0.000%

    No Known Activations