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
     remembered
    -0.07
    webs
    -0.07
     McCoy
    -0.06
     affection
    -0.06
    79
    -0.06
    Feature
    -0.06
    縮
    -0.06
     absolute
    -0.06
     flame
    -0.06
    PopupMenu
    -0.06
    POSITIVE LOGITS
    :block
    0.07
     Nombre
    0.07
     belirtilen
    0.07
    ANDLE
    0.06
     hern
    0.06
     #[
    0.06
    .CurrentCulture
    0.06
     gente
    0.06
     受
    0.06
     각
    0.06
    Act Density 0.001%

    No Known Activations