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

    Neuronpedia

    INDEX
    Explanations

    legal opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adopting
    -0.07
    928
    -0.07
    .Listener
    -0.06
    -*-
    -0.06
    -debug
    -0.06
    (cube
    -0.06
    _CUBE
    -0.06
     refuse
    -0.06
    906
    -0.06
    		 ↵
    -0.06
    POSITIVE LOGITS
    yme
    0.07
    δο
    0.06
     BTN
    0.06
     AX
    0.06
    SPACE
    0.06
     UX
    0.06
     Pied
    0.06
     vững
    0.06
    _verbose
    0.05
     CX
    0.05
    Act Density 0.007%

    No Known Activations