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

    Neuronpedia

    INDEX
    Explanations

    references to maintenance and road conditions

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

    followed by prepositions/punctuation

    np_acts-logits-general · gemini-2.0-flash

    condition, shape, or circumstances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ministre
    -0.89
     coté
    -0.86
     noël
    -0.86
    cektir
    -0.81
     delà
    -0.81
     Schluß
    -0.81
     skall
    -0.80
     didalam
    -0.80
     daß
    -0.80
     idag
    -0.79
    POSITIVE LOGITS
     
    0.95
     
    0.94
    ),”
    0.88
    ,’’
    0.88
     Sebab
    0.84
    ),"
    0.84
    .—
    0.83
     amid
    0.81
    ],"
    0.80
    .–
    0.78
    Act Density 0.210%

    No Known Activations