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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ansch
    -0.06
    ţi
    -0.06
     Highly
    -0.06
    -tra
    -0.06
     replication
    -0.06
    ксп
    -0.06
    ebek
    -0.06
    θν
    -0.06
     Symbol
    -0.06
    WritableDatabase
    -0.06
    POSITIVE LOGITS
     announce
    0.07
    评价
    0.07
     fragrance
    0.07
    exception
    0.06
    alarında
    0.06
    给我
    0.06
    hora
    0.06
     certainty
    0.06
    érica
    0.06
    |:
    0.06
    Act Density 0.002%

    No Known Activations