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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .valor
    -0.08
     odak
    -0.07
    ่งข
    -0.07
    ographs
    -0.07
    ']."
    -0.07
    後に
    -0.06
    ンフ
    -0.06
    _HEAD
    -0.06
     libr
    -0.06
     Gameplay
    -0.06
    POSITIVE LOGITS
     Candidates
    0.06
     jeopard
    0.06
    َة
    0.06
     김
    0.06
    дал
    0.06
    (my
    0.06
     Supervisor
    0.06
    ніцип
    0.06
     deepen
    0.05
     integrate
    0.05
    Act Density 0.000%

    No Known Activations