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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash

    finds modal and auxiliary verbs (words expressing ability, necessity, or possibility such as can, must, will, be).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     dönüş
    -0.07
    -hooks
    -0.07
    сим
    -0.07
    اهی
    -0.07
    .Lock
    -0.06
    ��
    -0.06
    _PREVIEW
    -0.06
     eos
    -0.06
    .ast
    -0.06
    owed
    -0.06
    POSITIVE LOGITS
     However
    0.07
    .company
    0.07
     Advice
    0.07
    However
    0.07
    -Out
    0.06
     }
↵
    0.06
     Down
    0.06
    ，存于
    0.06
     jenis
    0.06
     /**
    0.06
    Act Density 1.254%

    No Known Activations