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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     probably
    -0.07
    iene
    -0.07
    ihad
    -0.07
     Bruins
    -0.07
    _DS
    -0.07
     đều
    -0.06
    しゃ
    -0.06
    .ext
    -0.06
     always
    -0.06
    izzly
    -0.06
    POSITIVE LOGITS
     blooms
    0.06
     Cuando
    0.06
    	Status
    0.06
    HeaderValue
    0.06
     LIVE
    0.06
     Fiction
    0.06
    INTERNAL
    0.06
     showAlert
    0.06
    .between
    0.06
     Democr
    0.06
    Act Density 0.017%

    No Known Activations