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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SETTING
    -0.07
    /latest
    -0.07
    .Align
    -0.07
    Thunk
    -0.07
    "/>↵
    -0.06
    .buf
    -0.06
    жив
    -0.06
     Sixth
    -0.06
    _routing
    -0.06
     обст
    -0.06
    POSITIVE LOGITS
    ippo
    0.07
    ανδ
    0.07
     mutlaka
    0.06
     mattered
    0.06
     educators
    0.06
    ование
    0.06
     recommendation
    0.06
     finalized
    0.06
     Тому
    0.06
     mücadele
    0.06
    Act Density 0.029%

    No Known Activations