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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bounds
    -0.07
    ертв
    -0.07
    スト
    -0.06
    бов
    -0.06
    ウィ
    -0.06
    -Ф
    -0.06
    .break
    -0.06
    ành
    -0.06
     χρό
    -0.06
    ής
    -0.06
    POSITIVE LOGITS
     coeffs
    0.06
     Simpl
    0.06
    (Target
    0.06
    .VisualBasic
    0.06
     sistemi
    0.06
     Dominion
    0.06
     anticipate
    0.06
     Captain
    0.06
    	progress
    0.06
     subtype
    0.06
    Act Density 0.000%

    No Known Activations