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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    compile
    -0.07
    tryside
    -0.06
    openh
    -0.06
    HAV
    -0.06
    izzazione
    -0.06
     remorse
    -0.06
    ísto
    -0.06
    ыџN
    -0.06
    ি
    -0.06
    uki
    -0.05
    POSITIVE LOGITS
    _tac
    0.07
     DIM
    0.07
     '.',
    0.07
     NK
    0.07
    شن
    0.07
    .Σ
    0.07
    _()↵
    0.06
     Persist
    0.06
    (IO
    0.06
    亦
    0.06
    Act Density 0.037%

    No Known Activations