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

    Neuronpedia

    INDEX
    Explanations

    control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (inst
    -0.07
    getVar
    -0.07
    дяки
    -0.07
    .zoom
    -0.06
     значення
    -0.06
     आक
    -0.06
     <->
    -0.06
    SURE
    -0.06
     Highly
    -0.06
     Arb
    -0.06
    POSITIVE LOGITS
    _hist
    0.07
    percentage
    0.06
    geries
    0.06
     pev
    0.06
    amount
    0.06
    鼻
    0.06
     Vocabulary
    0.06
     žal
    0.06
    collection
    0.06
    connexion
    0.06
    Act Density 0.026%

    No Known Activations