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

    Neuronpedia

    INDEX
    Explanations

    arrangements and adjacency

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Canary
    -0.09
     schö
    -0.08
    basis
    -0.08
    batch
    -0.08
    _VALUES
    -0.08
    SUPPORTED
    -0.08
     поступ
    -0.08
     Basel
    -0.08
     authenticate
    -0.08
    _STREAM
    -0.08
    POSITIVE LOGITS
     arrangements
    0.12
     adjacency
    0.12
     arrangement
    0.10
     pair
    0.10
     adjacent
    0.10
     distance
    0.09
     pairs
    0.09
     Abstand
    0.09
    _pairs
    0.09
     interactions
    0.09
    Act Density 0.016%

    No Known Activations