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
    ";"
    -0.08
    設備
    -0.07
    /devices
    -0.07
    _download
    -0.07
     gypsum
    -0.07
    lerle
    -0.07
     resultado
    -0.07
     viet
    -0.06
    	EXPECT
    -0.06
     pronounced
    -0.06
    POSITIVE LOGITS
     oferta
    0.06
    (Column
    0.06
     indefinite
    0.06
    246
    0.06
    iscrim
    0.05
     간
    0.05
     podr
    0.05
     society
    0.05
    wil
    0.05
    เจร
    0.05
    Act Density 0.002%

    No Known Activations