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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æľī幸
    -0.26
    riz
    -0.25
     moments
    -0.25
    kart
    -0.25
     unequal
    -0.24
     reductions
    -0.24
    éĤº
    -0.24
    amarin
    -0.24
    pars
    -0.24
    UIScreen
    -0.24
    POSITIVE LOGITS
    交ä»ĺ
    0.32
    åIJĮç±»
    0.27
    ness
    0.27
    éĢĿ
    0.26
    .ht
    0.25
     inspected
    0.25
     timestamp
    0.25
    俶
    0.24
    phis
    0.24
    timestamp
    0.24
    Act Density 0.014%

    No Known Activations