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

    Neuronpedia

    INDEX
    Explanations

    add, remove, revoke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sigh
    0.43
    TypeText
    0.42
     $((
    0.41
     nahil
    0.41
    fti
    0.40
     Така
    0.39
     শাখা
    0.39
     $\{(
    0.38
    ertura
    0.38
    Sides
    0.38
    POSITIVE LOGITS
    summon
    0.44
    EventListener
    0.41
     data
    0.39
     MonoBehaviour
    0.38
     existe
    0.38
     impl
    0.38
     MON
    0.37
     improvised
    0.37
    汛
    0.37
     MARC
    0.37
    Act Density 0.000%

    No Known Activations