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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    éo
    -0.34
    udit
    -0.28
    ropri
    -0.27
    ign
    -0.26
    zano
    -0.26
    ÄĻ
    -0.24
     Kerr
    -0.24
     biá»ĩn
    -0.24
    unities
    -0.24
    WAY
    -0.24
    POSITIVE LOGITS
    æ´¾
    0.29
    :variables
    0.25
     potency
    0.24
    游æĪıçݩ家
    0.24
    çªĹ
    0.24
    ðŁIJį
    0.24
    æ´¾åĩº
    0.24
     minimalist
    0.23
    alking
    0.23
    .Compile
    0.23
    Act Density 0.005%

    No Known Activations