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

    Neuronpedia

    INDEX
    Explanations

    those

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Honour
    -0.07
     dint
    -0.07
     educ
    -0.07
    inan
    -0.07
     rounded
    -0.07
    modified
    -0.07
    _generate
    -0.07
    =c
    -0.07
     solicit
    -0.06
     dining
    -0.06
    POSITIVE LOGITS
    しょう
    0.06
     Hydro
    0.06
     GOLD
    0.06
    เผ
    0.06
     kell
    0.06
     Пло
    0.06
    ゲ
    0.06
    gold
    0.05
    BufferSize
    0.05
     Hel
    0.05
    Act Density 0.000%

    No Known Activations