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

    Neuronpedia

    INDEX
    Explanations

    novelty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Get
    -0.08
     Dek
    -0.08
    Ash
    -0.07
    Dict
    -0.07
    _FLUSH
    -0.06
    _connected
    -0.06
    dig
    -0.06
    _Work
    -0.06
    _PK
    -0.06
    Ing
    -0.06
    POSITIVE LOGITS
     oyn
    0.06
     inevitable
    0.06
     seasonal
    0.06
     domination
    0.06
     bước
    0.06
     argued
    0.06
     alguien
    0.06
     sensory
    0.06
     accompagn
    0.06
    mass
    0.06
    Act Density 0.026%

    No Known Activations