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

    Neuronpedia

    INDEX
    Explanations

    Arkansas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    okus
    -0.08
     prakt
    -0.07
    PWM
    -0.07
    暇
    -0.07
    令
    -0.07
     dealings
    -0.07
    _NOP
    -0.07
     Hague
    -0.07
    理念
    -0.07
     whisky
    -0.07
    POSITIVE LOGITS
    公共
    0.07
    ='-
    0.07
     Down
    0.07
     arrogant
    0.07
    �
    0.07
    档案
    0.07
    צביע
    0.07
     müşteri
    0.07
    Ƨ
    0.07
    させて
    0.06
    Act Density 0.008%

    No Known Activations