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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avoir
    -0.07
     preventive
    -0.07
     CAL
    -0.07
     Gregory
    -0.07
     NAS
    -0.06
     Hector
    -0.06
     revealing
    -0.06
     Arc
    -0.06
     heavy
    -0.06
     ihn
    -0.06
    POSITIVE LOGITS
    /device
    0.07
    -प
    0.07
    foods
    0.06
     voksne
    0.06
     sass
    0.06
     justifyContent
    0.06
    □
    0.06
    _wait
    0.06
    mut
    0.06
     studi
    0.06
    Act Density 0.025%

    No Known Activations