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

    Neuronpedia

    INDEX
    Explanations

    conv

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mis
    -0.07
     Lý
    -0.07
    ừ
    -0.07
     ObjectType
    -0.07
    ---------
    -0.07
     To
    -0.07
    aul
    -0.07
    -handler
    -0.07
    Resources
    -0.07
    你应该
    -0.07
    POSITIVE LOGITS
     cnn
    0.07
     لتح
    0.07
    MMdd
    0.07
    惯例
    0.07
    ◜
    0.07
     Innovative
    0.06
     iliş
    0.06
     cu
    0.06
    珐
    0.06
     Spa
    0.06
    Act Density 0.015%

    No Known Activations