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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prefs
    -0.07
    彼
    -0.06
    ,readonly
    -0.06
     Ker
    -0.06
    čel
    -0.06
    ceptar
    -0.06
     groove
    -0.06
     Village
    -0.06
    project
    -0.06
     blasph
    -0.06
    POSITIVE LOGITS
     trademark
    0.07
    挺
    0.07
     got
    0.06
     term
    0.06
    ิงหาคม
    0.06
     восстанов
    0.06
    ітет
    0.06
     {$
    0.06
     anth
    0.06
     consistently
    0.06
    Act Density 0.008%

    No Known Activations