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

    Neuronpedia

    INDEX
    Explanations

    mandatory expressions or obligations

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

    "Must" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    Must be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endphp
    -0.98
     GenerationType
    -0.91
    DockStyle
    -0.85
    aarrggbb
    -0.85
    ViewFeatures
    -0.77
    Portale
    -0.75
    abestanden
    -0.74
     Olympedia
    -0.72
    AndEndTag
    -0.71
    IsMutable
    -0.70
    POSITIVE LOGITS
     Must
    0.92
     surely
    0.88
    Must
    0.87
     MUST
    0.86
     must
    0.85
     always
    0.77
     be
    0.77
    MUST
    0.74
    must
    0.72
     mustn
    0.70
    Act Density 0.054%

    No Known Activations