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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    »)
    -0.08
     &
    -0.07
    	Button
    -0.06
     Americans
    -0.06
     Ange
    -0.06
     alcohol
    -0.06
    Qual
    -0.06
    Fonts
    -0.06
     monde
    -0.06
     automobile
    -0.06
    POSITIVE LOGITS
    らい
    0.07
    してい
    0.07
    ocomplete
    0.06
     pj
    0.06
    .gui
    0.06
     kıl
    0.06
     cancellation
    0.06
     #+#
    0.06
     tying
    0.06
    iç
    0.06
    Act Density 0.010%

    No Known Activations