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

    Neuronpedia

    INDEX
    Explanations

    phenomena and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     COMMUNITY
    0.43
     Rfe
    0.43
     CORPER
    0.43
    ArchivePath
    0.42
     difficol
    0.41
     CI
    0.41
     xy
    0.41
     rije
    0.40
     Ranked
    0.40
    ොර
    0.40
    POSITIVE LOGITS
    ach
    0.55
    duction
    0.54
    J
    0.52
    H
    0.49
    ene
    0.49
    sp
    0.48
    ato
    0.47
    roup
    0.47
    est
    0.47
     ح
    0.47
    Act Density 0.000%

    No Known Activations