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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _kv
    -0.07
    .encoder
    -0.07
    _LT
    -0.07
    聖
    -0.07
    (nt
    -0.07
     núi
    -0.06
     ště
    -0.06
     نفت
    -0.06
     pazar
    -0.06
    ombat
    -0.06
    POSITIVE LOGITS
    osis
    0.10
    cos
    0.08
    inois
    0.08
    asis
    0.08
     memoir
    0.07
     Περι
    0.07
    ΥΣ
    0.07
     аром
    0.07
    IS
    0.07
     wishlist
    0.07
    Act Density 0.005%

    No Known Activations