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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emergency
    -0.09
     emergency
    -0.09
    ۹
    -0.07
    observation
    -0.07
    Ross
    -0.07
    WritableDatabase
    -0.07
     cries
    -0.07
     Pays
    -0.07
    Gap
    -0.06
    Flow
    -0.06
    POSITIVE LOGITS
     liked
    0.09
     liking
    0.08
     lire
    0.08
     pleasant
    0.07
     springfox
    0.07
     disliked
    0.07
    ection
    0.06
     likes
    0.06
    .List
    0.06
    んど
    0.06
    Act Density 0.043%

    No Known Activations