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

    Neuronpedia

    INDEX
    Explanations

    presence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    كسب
    -0.08
    ën
    -0.08
    ENV
    -0.07
    Hold
    -0.07
     B
    -0.07
    new
    -0.06
     isbn
    -0.06
    KC
    -0.06
    ercial
    -0.06
    unted
    -0.06
    POSITIVE LOGITS
    şek
    0.07
     zwischen
    0.07
    >T
    0.07
    ?action
    0.07
    	None
    0.06
    Ⲡ
    0.06
    延续
    0.06
     bamb
    0.06
    _tensors
    0.06
    蚊
    0.06
    Act Density 0.001%

    No Known Activations