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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mailed
    -0.07
    洋葱
    -0.07
    età
    -0.07
    ADED
    -0.07
    _Delay
    -0.07
    	Get
    -0.06
    喳
    -0.06
    แช
    -0.06
    .removeFrom
    -0.06
     eğlen
    -0.06
    POSITIVE LOGITS
     targeted
    0.06
    �
    0.06
     Lit
    0.06
    .SP
    0.06
     offshore
    0.06
    目前国内
    0.06
     South
    0.06
    为目标
    0.06
    uke
    0.06
    心里
    0.06
    Act Density 0.033%

    No Known Activations