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

    Neuronpedia

    INDEX
    Explanations

    colons and equals signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     serait
    -0.06
    #######
    -0.06
    [level
    -0.06
    ########################################
    -0.06
    mega
    -0.06
    ietet
    -0.06
     lehet
    -0.06
    1
    -0.06
    	re
    -0.06
     impost
    -0.06
    POSITIVE LOGITS
     ErrorMessage
    0.07
    .addTarget
    0.06
    าษฎร
    0.06
    …”↵↵
    0.06
    .Read
    0.06
     Checkbox
    0.06
     vb
    0.06
     τη
    0.06
    .Context
    0.06
     університет
    0.06
    Act Density 0.034%

    No Known Activations