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

    Neuronpedia

    INDEX
    Explanations

    Grammatically correct English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perhaps
    -0.06
     Locale
    -0.06
    RFC
    -0.06
     bize
    -0.06
     происходит
    -0.06
     Raq
    -0.06
     Clar
    -0.06
     ruku
    -0.06
     mass
    -0.06
     Capital
    -0.06
    POSITIVE LOGITS
    Safety
    0.07
     prostitution
    0.06
    ]:↵↵↵
    0.06
     modificar
    0.06
    755
    0.06
    ]):↵
    0.06
    preferences
    0.06
    ريس
    0.06
    toolStrip
    0.06
     opens
    0.06
    Act Density 0.000%

    No Known Activations