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

    Neuronpedia

    INDEX
    Explanations

    bounded

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     concurrently
    -0.06
     อ
    -0.06
     Damn
    -0.06
    。但
    -0.06
     नह
    -0.06
    ynchronized
    -0.06
     Ου
    -0.06
    anni
    -0.06
    .author
    -0.06
     witnessing
    -0.06
    POSITIVE LOGITS
    InputDialog
    0.07
    lenmiş
    0.07
    _RS
    0.06
     deport
    0.06
    :self
    0.06
     귀
    0.06
     RETURN
    0.06
     OB
    0.06
     Trav
    0.06
     Rewards
    0.06
    Act Density 0.040%

    No Known Activations