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

    Neuronpedia

    INDEX
    Explanations

    Action words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Traits
    -0.07
    _DIRS
    -0.06
     있
    -0.06
    ァ
    -0.06
    牛
    -0.06
    งน
    -0.06
     Lear
    -0.06
    チ
    -0.06
     интер
    -0.06
     루
    -0.06
    POSITIVE LOGITS
    (parseInt
    0.07
    ToSend
    0.07
    umbles
    0.07
     وفي
    0.07
     concentrate
    0.06
     mediante
    0.06
     greatest
    0.06
    _HARD
    0.06
    (links
    0.06
    assertFalse
    0.06
    Act Density 0.290%

    No Known Activations