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

    Neuronpedia

    INDEX
    Explanations

    is are were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sacr
    -0.07
     swing
    -0.07
     frozen
    -0.07
    är
    -0.06
    편
    -0.06
     clutch
    -0.06
    .updateDynamic
    -0.06
     nation
    -0.06
    ,body
    -0.06
     pudd
    -0.06
    POSITIVE LOGITS
     Abilities
    0.07
     resembl
    0.07
     nun
    0.06
    [%
    0.06
     науков
    0.06
    	rb
    0.06
    (logging
    0.06
     uvědom
    0.05
    uite
    0.05
     Baum
    0.05
    Act Density 0.161%

    No Known Activations