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

    Neuronpedia

    INDEX
    Explanations

    General

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rů
    -0.07
    енный
    -0.07
    …↵
    -0.06
    ربی
    -0.06
     mulheres
    -0.06
    reece
    -0.06
    615
    -0.06
    _VLAN
    -0.06
     查询
    -0.06
    ροφορ
    -0.06
    POSITIVE LOGITS
     rose
    0.07
     apartment
    0.07
     Steele
    0.06
    (des
    0.06
    athlete
    0.06
     fiscal
    0.06
     apartments
    0.06
     tome
    0.06
     alg
    0.06
    acic
    0.06
    Act Density 0.014%

    No Known Activations