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

    Neuronpedia

    INDEX
    Explanations

    Year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    すす
    -0.07
     setw
    -0.07
     overridden
    -0.06
     suất
    -0.06
    ,",
    -0.06
     лучше
    -0.06
     empt
    -0.06
     pity
    -0.06
     जह
    -0.06
    薦
    -0.06
    POSITIVE LOGITS
    pch
    0.07
    Creative
    0.06
    aceae
    0.06
    imation
    0.06
    Ast
    0.06
    odesk
    0.06
    PG
    0.06
     diffs
    0.06
    _dyn
    0.06
    mad
    0.06
    Act Density 0.001%

    No Known Activations