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

    Neuronpedia

    INDEX
    Explanations

    references to significant or deep insights and changes in context

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

    profound significance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.72
    KURZBESCHREIBUNG
    -0.63
     Latch
    -0.57
    дравству
    -0.56
     getCity
    -0.55
     ligiloj
    -0.55
     calendriers
    -0.55
     mistress
    -0.54
    Shir
    -0.54
     Chriftian
    -0.54
    POSITIVE LOGITS
     profound
    1.94
     profoundly
    1.43
     profundo
    1.02
     profundos
    0.96
     profonda
    0.95
     profund
    0.93
     profunda
    0.90
     profondo
    0.85
     profundas
    0.83
     profonde
    0.81
    Act Density 0.005%

    No Known Activations