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

    Neuronpedia

    INDEX
    Explanations

    specific titles and names related to movies or literary works

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

    Follows quotation marks (") or angle brackets (>)

    np_acts-logits-general · gemini-2.0-flash

    strings from localization files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ''');
    -0.49
    …,
    -0.46
    --
    -0.45
    Спољашње
    -0.44
    ".$_
    -0.44
    .}\
    -0.43
    ----------
    -0.41
    esterday
    -0.40
    ²)
    -0.40
    ondag
    -0.38
    POSITIVE LOGITS
     تضيفلها
    1.19
     HasFactory
    1.03
    Datuak
    1.01
    afficheront
    0.94
    djangoproject
    0.88
    __(/*!
    0.87
     ligiloj
    0.86
    UnknownFields
    0.85
    addContainerGap
    0.85
     '\\;'
    0.84
    Act Density 0.148%

    No Known Activations