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

    Neuronpedia

    INDEX
    Explanations

    Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DAQ
    -0.07
    ilitary
    -0.06
    bens
    -0.06
     novelty
    -0.06
    킅
    -0.06
    mul
    -0.06
     meaningless
    -0.06
     femmes
    -0.06
     fraudulent
    -0.06
    勋
    -0.06
    POSITIVE LOGITS
     acompan
    0.07
     admissions
    0.07
    \Storage
    0.07
    クラス
    0.07
     (("
    0.07
     componentDid
    0.07
    🍸
    0.07
     redistribute
    0.06
    Cre
    0.06
     Tasmania
    0.06
    Act Density 0.067%

    No Known Activations