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

    Neuronpedia

    INDEX
    Explanations

    people/list of names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     misuse
    -0.06
    Чер
    -0.06
    ynes
    -0.06
    Positive
    -0.06
    ned
    -0.06
    ẹn
    -0.06
    literal
    -0.06
     illustrates
    -0.05
    237
    -0.05
    _FAILURE
    -0.05
    POSITIVE LOGITS
    odní
    0.07
     Gum
    0.07
    /thread
    0.06
    _softc
    0.06
    ::{
    0.06
    	Page
    0.06
    …and
    0.06
     lemma
    0.06
     reklam
    0.06
     ^{[
    0.06
    Act Density 0.131%

    No Known Activations