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

    Neuronpedia

    INDEX
    Explanations

    need

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     genom
    -0.06
    헌
    -0.06
     대전
    -0.06
     senha
    -0.06
     okul
    -0.06
    あげ
    -0.06
     Westbrook
    -0.06
     bure
    -0.06
     catchy
    -0.06
     Ment
    -0.06
    POSITIVE LOGITS
     onResponse
    0.07
    Particle
    0.07
    /router
    0.07
     suffer
    0.06
    Rep
    0.06
    inand
    0.06
    |:
    0.06
     É
    0.06
    _FROM
    0.06
    doctype
    0.06
    Act Density 0.119%

    No Known Activations