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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions related to absolute values

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

    Mathematical notation involving brackets and symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nawr
    -0.65
    FontStyle
    -0.65
    MergeFrom
    -0.60
    ::-
    -0.58
    oneofs
    -0.57
     resourceCulture
    -0.57
    
    -0.56
    судар
    -0.56
    -
    -0.54
     doInBackground
    -0.53
    POSITIVE LOGITS
    +|
    0.95
    .|
    0.90
     myſelf
    0.88
    -|
    0.88
     Jefus
    0.87
    ]|
    0.86
     purpoſe
    0.86
     auffi
    0.85
     $|
    0.84
     poffible
    0.80
    Act Density 0.170%

    No Known Activations