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

    Neuronpedia

    INDEX
    Explanations

    negative statements or expressions in the text

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

    not followed by a state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.59
     المعيارى
    -0.46
    orage
    -0.44
    InitStruct
    -0.42
     fieldNum
    -0.41
     ✭✭
    -0.41
    +#+#
    -0.40
     utafitiHapana
    -0.40
    juice
    -0.40
    foria
    -0.40
    POSITIVE LOGITS
     Италијани
    0.42
     saudável
    0.40
     publiques
    0.39
     neither
    0.39
     przypad
    0.38
     Szw
    0.37
    assertFalse
    0.37
    DockStyle
    0.36
     démocr
    0.36
    Neither
    0.36
    Act Density 0.139%

    No Known Activations