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

    Neuronpedia

    INDEX
    Explanations

    scientific discoveries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eut
    -0.07
    ctal
    -0.06
    riba
    -0.06
    Dup
    -0.06
     jego
    -0.06
    	for
    -0.06
    рукту
    -0.06
     protection
    -0.06
     метод
    -0.06
     KP
    -0.06
    POSITIVE LOGITS
    摇
    0.07
     önlem
    0.07
    nost
    0.07
    難
    0.07
    のような
    0.07
    �
    0.06
    StateToProps
    0.06
     -$
    0.06
    ，把
    0.06
    -original
    0.06
    Act Density 0.070%

    No Known Activations