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

    Neuronpedia

    INDEX
    Explanations

    Code and libraries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     -*-
↵
    -0.06
     QLabel
    -0.06
     contradictory
    -0.06
    ',↵↵
    -0.06
     BLE
    -0.06
     cdr
    -0.06
     조회
    -0.06
    !')↵↵
    -0.06
     IDC
    -0.06
    clearfix
    -0.06
    POSITIVE LOGITS
    nia
    0.07
    appa
    0.07
    ağ
    0.07
    lâm
    0.07
    rowth
    0.07
    xFFFFFF
    0.06
    يمي
    0.06
    ifying
    0.06
    ارس
    0.06
    aturated
    0.06
    Act Density 0.000%

    No Known Activations