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

    Neuronpedia

    INDEX
    Explanations

    describing a process

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    艦
    -0.07
    Thêm
    -0.07
     htt
    -0.07
    ARGE
    -0.07
     Resp
    -0.06
    局
    -0.06
    iky
    -0.06
     inventions
    -0.06
    рукту
    -0.06
     legalization
    -0.06
    POSITIVE LOGITS
     Aster
    0.06
    iel
    0.06
    Measured
    0.06
     Covenant
    0.06
     
    0.06
     showcased
    0.06
    ,and
    0.06
     abusive
    0.06
     fairness
    0.06
     CLEAR
    0.06
    Act Density 0.057%

    No Known Activations