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

    Neuronpedia

    INDEX
    Explanations

    Software applications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wine
    -0.07
    _Date
    -0.07
    SError
    -0.07
    inja
    -0.07
     rab
    -0.07
     layout
    -0.07
     JOIN
    -0.07
    -column
    -0.07
     nomin
    -0.07
     THR
    -0.07
    POSITIVE LOGITS
    [mid
    0.07
    high
    0.06
     обязатель
    0.06
    JKLMNOP
    0.06
    сол
    0.06
    	pop
    0.06
     εμπ
    0.06
    ')))↵
    0.06
    ]↵↵
    0.06
     Ticaret
    0.05
    Act Density 0.056%

    No Known Activations