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

    Neuronpedia

    INDEX
    Explanations

    independent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    يلاد
    -0.06
     clot
    -0.06
     buộc
    -0.06
    (Common
    -0.06
     afirm
    -0.06
    まる
    -0.06
     Singh
    -0.06
    riting
    -0.06
     člen
    -0.06
     courtroom
    -0.06
    POSITIVE LOGITS
    .Th
    0.07
    )x
    0.07
     cumulative
    0.07
     dlg
    0.07
     masculine
    0.07
     nedeni
    0.06
    PIP
    0.06
    プリ
    0.06
     Epic
    0.06
    cul
    0.06
    Act Density 0.004%

    No Known Activations