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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     local
    -0.68
     nakalista
    -0.59
     moral
    -0.58
     global
    -0.55
     natural
    -0.51
     the
    -0.50
     horizontal
    -0.50
     beautiful
    -0.49
     personal
    -0.49
     legal
    -0.49
    POSITIVE LOGITS
    Referanser
    0.68
    日閲覧
    0.68
     שוליים
    0.65
    Incident
    0.64
     HttpNotFound
    0.61
    لكتر
    0.60
     tacón
    0.59
    Revenir
    0.59
    FunctionFlags
    0.57
    OOTDTY
    0.57
    Act Density 0.003%

    No Known Activations