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

    Neuronpedia

    INDEX
    Explanations

    probably

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    063
    -0.07
    ise
    -0.07
    ict
    -0.06
    ("/")↵
    -0.06
    ΙΣ
    -0.06
     ethers
    -0.06
    isors
    -0.06
     census
    -0.06
    _verification
    -0.06
     highlighted
    -0.06
    POSITIVE LOGITS
     probably
    0.19
    probably
    0.16
     Probably
    0.14
    Probably
    0.14
    hydr
    0.08
     那
    0.08
     Probability
    0.08
     probable
    0.07
    .people
    0.07
    prob
    0.07
    Act Density 0.011%

    No Known Activations