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

    Neuronpedia

    INDEX
    Explanations

    paras

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Tile
    -0.07
     Indi
    -0.07
    uncios
    -0.06
    احة
    -0.06
    (proj
    -0.06
     datos
    -0.06
     OCI
    -0.06
     imap
    -0.06
     maneuver
    -0.06
    uiten
    -0.06
    POSITIVE LOGITS
     researchers
    0.07
     hopeless
    0.07
    (AdapterView
    0.07
     thro
    0.07
     الکتر
    0.06
    	Entity
    0.06
    ynamic
    0.06
    .getStart
    0.06
     Accuracy
    0.06
    Destination
    0.06
    Act Density 0.014%

    No Known Activations