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

    Neuronpedia

    INDEX
    Explanations

    call or email

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     narr
    -0.07
    Detail
    -0.07
    今日
    -0.06
     katılım
    -0.06
    belief
    -0.06
     hoạch
    -0.06
     أكتوبر
    -0.06
    $I
    -0.06
     Aydın
    -0.06
    模
    -0.06
    POSITIVE LOGITS
    シェ
    0.08
    >V
    0.07
    967
    0.07
     experimenting
    0.06
     플레이
    0.06
    приєм
    0.06
     *)((
    0.06
    ]-
    0.06
    addPreferredGap
    0.06
     стати
    0.06
    Act Density 0.024%

    No Known Activations