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

    Neuronpedia

    INDEX
    Explanations

    l

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —are
    -0.06
     Huang
    -0.06
     Fortress
    -0.06
    	ev
    -0.06
     captive
    -0.06
    .YELLOW
    -0.06
    	Returns
    -0.06
    	Write
    -0.06
    	Update
    -0.06
     modes
    -0.06
    POSITIVE LOGITS
     subtle
    0.06
     सरक
    0.06
     fl
    0.06
    warehouse
    0.06
     Drink
    0.06
    ����
    0.06
     RL
    0.06
     sl
    0.06
    stdlib
    0.06
     -=
    0.06
    Act Density 0.001%

    No Known Activations