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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tor
    -0.08
     Iranian
    -0.07
    لمة
    -0.06
    _REGION
    -0.06
    adí
    -0.06
    Malloc
    -0.06
    اعات
    -0.06
    .Collections
    -0.06
    액
    -0.06
    427
    -0.06
    POSITIVE LOGITS
     lég
    0.08
    written
    0.07
     Zucker
    0.07
     foundational
    0.06
     lia
    0.06
     koneč
    0.06
    .z
    0.06
    ˆ
    0.06
     ​​​
    0.06
     unit
    0.06
    Act Density 0.002%

    No Known Activations