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

    Neuronpedia

    INDEX
    Explanations

    Code and database schemas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gener
    -0.09
     gener
    -0.08
    aih
    -0.08
    cen
    -0.08
    /results
    -0.08
    magn
    -0.07
     estim
    -0.07
    /world
    -0.07
    linear
    -0.07
    disp
    -0.07
    POSITIVE LOGITS
     valid
    0.12
    .Valid
    0.12
    Valid
    0.12
    .valid
    0.12
     Valid
    0.12
     gült
    0.12
    _VALID
    0.11
    (valid
    0.11
    	valid
    0.11
    valid
    0.11
    Act Density 0.009%

    No Known Activations