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

    Neuronpedia

    INDEX
    Explanations

    text associated with numerical data or statistical references

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

    Numbers followed by letters

    np_acts-logits-general · gemini-2.0-flash

    "a" or "b" followed by letters/numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.84
    liothèque
    -0.70
    EndProject
    -0.69
    GOTREF
    -0.68
    المكان
    -0.66
    }';
    -0.66
     насељу
    -0.66
    хьтан
    -0.65
    IUrlHelper
    -0.65
     ]];
    -0.64
    POSITIVE LOGITS
    a
    1.41
    b
    1.30
    A
    1.16
    B
    1.06
    bis
    0.88
    c
    0.76
     b
    0.71
    а
    0.71
    б
    0.64
    AB
    0.64
    Act Density 1.388%

    No Known Activations