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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    htable
    -0.07
     jaar
    -0.06
    waukee
    -0.06
     thumb
    -0.06
    ampions
    -0.06
     pakistan
    -0.06
    storm
    -0.06
    (),
    -0.06
    ेह
    -0.05
     choisir
    -0.05
    POSITIVE LOGITS
     Mont
    0.07
    �
    0.07
     Trit
    0.06
     [])
    0.06
     tout
    0.06
     rallying
    0.06
    Route
    0.06
    .setAuto
    0.06
     Gren
    0.06
    ("//*[@
    0.06
    Act Density 0.061%

    No Known Activations