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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Be
    -0.07
    liche
    -0.07
    :date
    -0.07
     convo
    -0.07
    sharing
    -0.06
    	reader
    -0.06
    noise
    -0.06
     drink
    -0.06
    352
    -0.06
    ​
    -0.06
    POSITIVE LOGITS
     frameworks
    0.07
    clidean
    0.06
     CIF
    0.06
    COORD
    0.06
    asterxml
    0.06
     emp
    0.06
    (inertia
    0.06
     Olivier
    0.06
    Als
    0.06
     Hampshire
    0.06
    Act Density 0.012%

    No Known Activations