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

    Neuronpedia

    INDEX
    Explanations

    moved

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Fl
    -0.08
    edriver
    -0.06
    الح
    -0.06
     čin
    -0.06
    GGLE
    -0.06
    _ts
    -0.06
    �
    -0.06
    orton
    -0.06
    -ves
    -0.06
     установки
    -0.06
    POSITIVE LOGITS
     /[
    0.07
    abama
    0.07
     cryptocurrencies
    0.07
     arrived
    0.07
     static
    0.06
     dood
    0.06
     coordinator
    0.06
    ____
    0.06
     advertising
    0.06
     agreed
    0.06
    Act Density 0.000%

    No Known Activations