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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated operations or relationships

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

    Numbers in tabular data

    np_acts-logits-general · gemini-2.0-flash

    hyphen after numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oprot
    -0.73
    ništ
    -0.62
     ostavi
    -0.62
    %</
    -0.60
    CppMethod
    -0.57
    🏾
    -0.57
    writeFieldEnd
    -0.57
    })).
    -0.57
    ="#">
    -0.56
    })),
    -0.56
    POSITIVE LOGITS
    SequentialGroup
    0.70
     végétale
    0.64
    ParallelGroup
    0.63
    jupiter
    0.61
     umana
    0.59
     يتيمه
    0.58
     fekete
    0.57
     Anſ
    0.57
     contextLoads
    0.56
     ſch
    0.56
    Act Density 0.063%

    No Known Activations