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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating names and identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the name of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     llenos
    -0.35
     concentrado
    -0.34
     antemano
    -0.33
    发表于
    -0.32
     begitu
    -0.31
     RVA
    -0.31
     dekorasi
    -0.30
    posedge
    -0.29
    tasche
    -0.29
    fscanf
    -0.28
    POSITIVE LOGITS
     ProtoMessage
    0.67
     surla
    0.67
     للمعارف
    0.60
     tartalomajánló
    0.58
     comuniques
    0.57
    LEncoder
    0.57
    LookAnd
    0.56
    hoeddwyd
    0.56
    VPB
    0.55
     GenerationType
    0.55
    Act Density 0.089%

    No Known Activations