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

    Neuronpedia

    INDEX
    Explanations

    special tokens and specific terms related to structured data or code

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

    Follows partial words

    np_acts-logits-general · gemini-2.0-flash

    legal and scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.81
     <<<<<<<<<<<<<<
    -0.69
    KURZBESCHREIBUNG
    -0.66
    tamol
    -0.64
    ✨:
    -0.62
     ambientale
    -0.62
     totales
    -0.62
     serons
    -0.61
     termica
    -0.61
    onAttach
    -0.61
    POSITIVE LOGITS
    ſelves
    0.98
    ſelf
    0.95
     Diſ
    0.82
    ſem
    0.81
     Perſ
    0.80
    eſ
    0.78
     iſt
    0.77
     Conſ
    0.77
    leſs
    0.76
     Inſ
    0.76
    Act Density 0.623%

    No Known Activations