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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and perspectives

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

    sequences indicating future or possession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.29
    copyWith
    -0.28
     esternos
    -0.28
     certification
    -0.28
    HasAnnotation
    -0.27
     rallado
    -0.26
     Emits
    -0.26
     dica
    -0.26
     surfaces
    -0.25
     nying
    -0.25
    POSITIVE LOGITS
    rungsseite
    0.77
     ligiloj
    0.59
    guerite
    0.51
    AutoresizingMask
    0.49
    asteroide
    0.48
    uver
    0.47
     spørs
    0.46
     accett
    0.46
    يكب
    0.45
    ropshire
    0.45
    Act Density 0.130%

    No Known Activations