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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xef
    -0.07
    outfile
    -0.06
    andoned
    -0.06
    Vict
    -0.06
    ets
    -0.06
     sle
    -0.06
     kelim
    -0.06
     Bj
    -0.06
    _pid
    -0.06
    ینی
    -0.06
    POSITIVE LOGITS
     باشگاه
    0.07
    阻
    0.07
     MLB
    0.06
    forming
    0.06
     GenerationType
    0.06
    .Priority
    0.06
    �
    0.06
    [file
    0.06
     ruby
    0.06
     Mistress
    0.06
    Act Density 0.005%

    No Known Activations