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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    れます
    -0.07
     inflater
    -0.07
    吃完
    -0.07
    发生的
    -0.06
    Billy
    -0.06
     למנוע
    -0.06
    Li
    -0.06
     disrupt
    -0.06
    大使
    -0.06
    .setMessage
    -0.06
    POSITIVE LOGITS
     played
    0.08
    _aff
    0.07
    ufact
    0.07
    aders
    0.07
    PGA
    0.07
    <data
    0.07
    ATAL
    0.07
     saturn
    0.06
    adata
    0.06
     Cavs
    0.06
    Act Density 0.010%

    No Known Activations