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

    Neuronpedia

    INDEX
    Explanations

    software versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     girl
    0.36
     Grit
    0.35
     CCCC
    0.34
    0.33
     젊
    0.33
     amel
    0.33
     tepl
    0.32
    鎸
    0.32
     कमाल
    0.32
     DBA
    0.32
    POSITIVE LOGITS
    rc
    0.71
    beta
    0.66
    RC
    0.64
    版本
    0.62
    RELEASE
    0.57
    dev
    0.55
    Beta
    0.54
    release
    0.52
    Rc
    0.52
    Release
    0.51
    Act Density 0.014%

    No Known Activations