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

    Neuronpedia

    INDEX
    Explanations

    Software licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ----------------------------------------------------------------------↵
    -0.06
    430
    -0.06
    loi
    -0.06
    Im
    -0.06
    altet
    -0.06
    ledger
    -0.06
     opendir
    -0.06
     �
    -0.06
    팅
    -0.06
    lerde
    -0.06
    POSITIVE LOGITS
     Nutrition
    0.07
    moving
    0.07
    ++++++++
    0.07
     Memory
    0.07
    :^(
    0.07
    (match
    0.06
     AH
    0.06
     Moving
    0.06
     melts
    0.06
     Invalid
    0.06
    Act Density 0.001%

    No Known Activations