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

    Neuronpedia

    INDEX
    Explanations

    code configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _price
    -0.07
    itbart
    -0.07
    allery
    -0.07
     کش
    -0.06
    ۱۵
    -0.06
    coins
    -0.06
    ную
    -0.06
    subcategory
    -0.06
     τον
    -0.06
     Write
    -0.06
    POSITIVE LOGITS
    .mutable
    0.07
     gamer
    0.06
    ffset
    0.06
    .Generation
    0.06
    "))
    0.06
     sudden
    0.06
     La
    0.06
    ")==
    0.06
     semester
    0.06
     chemicals
    0.06
    Act Density 0.004%

    No Known Activations