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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    宗
    -0.07
     haber
    -0.07
    edium
    -0.07
     Pol
    -0.07
     cand
    -0.07
     contentView
    -0.06
     myster
    -0.06
    "That
    -0.06
     Inf
    -0.06
     propertyName
    -0.06
    POSITIVE LOGITS
     flop
    0.06
     knocking
    0.06
     بهتر
    0.06
     getPrice
    0.06
    елі
    0.06
     mantra
    0.06
    Bag
    0.06
     uplifting
    0.06
     jl
    0.06
    同步
    0.06
    Act Density 0.004%

    No Known Activations