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

    Neuronpedia

    INDEX
    Explanations

    code identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    еров
    -0.07
    Send
    -0.06
    stackpath
    -0.06
    なし
    -0.06
    /disc
    -0.06
    GUILayout
    -0.06
    sexy
    -0.06
    classification
    -0.06
    ListBox
    -0.06
     sensory
    -0.06
    POSITIVE LOGITS
     CAUSED
    0.06
    asper
    0.06
     analsex
    0.06
     dara
    0.06
     ήταν
    0.06
     porrf
    0.06
    ICE
    0.06
    acic
    0.06
     ul
    0.06
     setError
    0.06
    Act Density 0.010%

    No Known Activations