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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TIME
    -0.07
     trending
    -0.07
     ------
    -0.07
    17
    -0.06
     二
    -0.06
     evolutionary
    -0.06
    Chapter
    -0.06
     tale
    -0.06
     blow
    -0.06
     [_
    -0.06
    POSITIVE LOGITS
     предназнач
    0.07
    SetActive
    0.07
     Lanka
    0.07
    žit
    0.06
    printStats
    0.06
    GRAPH
    0.06
     Vys
    0.06
    ůst
    0.06
     üye
    0.06
    .tar
    0.06
    Act Density 0.013%

    No Known Activations