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

    Neuronpedia

    INDEX
    Explanations

    Bureaucratic/Legal situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Export
    -0.08
    -0.07
    _variance
    -0.07
    原则上
    -0.07
     Students
    -0.07
    Insets
    -0.07
    南方
    -0.07
    notes
    -0.07
     flattened
    -0.07
     данный
    -0.06
    POSITIVE LOGITS
    ABEL
    0.07
     elect
    0.06
     ATH
    0.06
    (bit
    0.06
     ij
    0.06
     Qualität
    0.06
    اه
    0.06
     ");↵↵
    0.06
    الته
    0.06
    	offset
    0.06
    Act Density 0.051%

    No Known Activations