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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _daily
    -0.07
     ATTACK
    -0.07
     Appalach
    -0.07
     Necklace
    -0.07
     Highest
    -0.06
    政策
    -0.06
    ться
    -0.06
    uni
    -0.06
     Sour
    -0.06
    Sketch
    -0.06
    POSITIVE LOGITS
     فصل
    0.07
     aseg
    0.07
     frankly
    0.06
     відповід
    0.06
     باع
    0.06
     Phill
    0.06
    这么
    0.06
     lush
    0.06
     Weber
    0.06
     RSVP
    0.06
    Act Density 0.060%

    No Known Activations