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

    Neuronpedia

    INDEX
    Explanations

    conversational writing snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RG
    -0.06
     retrieved
    -0.06
    (row
    -0.06
     Над
    -0.06
    [first
    -0.06
    	ret
    -0.06
     facing
    -0.06
     UNKNOWN
    -0.06
    LowerCase
    -0.06
    _CUR
    -0.06
    POSITIVE LOGITS
    른
    0.07
    'i
    0.06
    (newUser
    0.06
     Virgin
    0.06
    ür
    0.06
    .frequency
    0.06
    Ve
    0.06
     thức
    0.06
    !↵↵↵↵↵↵
    0.06
    ;-
    0.06
    Act Density 0.006%

    No Known Activations