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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MK
    -0.07
    _FWD
    -0.06
    alk
    -0.06
     mata
    -0.06
     ICMP
    -0.06
    珍
    -0.06
    박
    -0.06
    縣
    -0.06
    MP
    -0.06
    _ov
    -0.06
    POSITIVE LOGITS
     Ancient
    0.07
     Karachi
    0.06
     приготовления
    0.06
     mouths
    0.06
    enzyme
    0.06
     český
    0.06
     gun
    0.06
     آذرب
    0.06
    icorn
    0.06
    multi
    0.06
    Act Density 0.016%

    No Known Activations