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

    Neuronpedia

    INDEX
    Explanations

    Guillermo del Toro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phase
    -0.07
     switched
    -0.07
     tenía
    -0.06
    .employee
    -0.06
     cultivated
    -0.06
     Problems
    -0.06
     CSP
    -0.06
     getElement
    -0.06
    .getItems
    -0.06
    ecta
    -0.06
    POSITIVE LOGITS
    arness
    0.07
    Ş
    0.06
     Allies
    0.06
    akra
    0.06
     setLoading
    0.06
    १
    0.06
    贝
    0.05
    celed
    0.05
    默
    0.05
    収
    0.05
    Act Density 0.011%

    No Known Activations