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

    Neuronpedia

    INDEX
    Explanations

    python code requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Man
    0.37
     Ris
    0.35
     L
    0.32
     S
    0.32
     Pers
    0.31
    Ins
    0.31
     blood
    0.30
    Rid
    0.30
    Conf
    0.30
     Rt
    0.30
    POSITIVE LOGITS
     হইয়৷
    0.37
     occuring
    0.37
    🖖
    0.37
    딕
    0.37
     введен
    0.37
     فريبي
    0.36
     функцию
    0.36
     মিথ
    0.35
     값을
    0.35
     функции
    0.35
    Act Density 0.001%

    No Known Activations