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

    Neuronpedia

    INDEX
    Explanations

    actions and activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (T
    -0.07
    -overlay
    -0.07
    _letters
    -0.06
    ている
    -0.06
    Thông
    -0.06
    왕
    -0.06
     xong
    -0.06
     वह
    -0.06
    _props
    -0.06
    たち
    -0.06
    POSITIVE LOGITS
     recursion
    0.07
     scient
    0.06
    Music
    0.06
     Coca
    0.06
    řet
    0.06
     Maze
    0.06
    	up
    0.06
     poisonous
    0.06
     ремонт
    0.06
    то
    0.06
    Act Density 0.454%

    No Known Activations