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

    Neuronpedia

    INDEX
    Explanations

    identification of prefixes and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recursive
    0.39
    เฉพาะ
    0.38
     implicit
    0.36
     rationale
    0.35
     Tier
    0.34
     tiered
    0.34
    ING
    0.33
     iterative
    0.33
     collaborative
    0.32
     persuasive
    0.32
    POSITIVE LOGITS
    và
    0.61
     whitish
    0.59
     ‘’
    0.56
     cloths
    0.56
    posizione
    0.56
     figurines
    0.55
    iduría
    0.55
    ización
    0.54
    oxyde
    0.54
    carros
    0.53
    Act Density 2.260%

    No Known Activations