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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    greater
    -0.07
     دام
    -0.06
     valid
    -0.06
    ded
    -0.06
    -center
    -0.06
     Phillips
    -0.06
     trường
    -0.06
    encia
    -0.06
    posed
    -0.06
     KeyValuePair
    -0.06
    POSITIVE LOGITS
     Anth
    0.07
    ,s
    0.07
     (↵↵
    0.07
     feeder
    0.07
    	scale
    0.06
     scale
    0.06
    _FIFO
    0.06
    .scale
    0.06
     plav
    0.06
     erot
    0.06
    Act Density 0.051%

    No Known Activations