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

    Neuronpedia

    INDEX
    Explanations

    provided

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lj
    -0.06
    ванов
    -0.06
     parasite
    -0.06
     biz
    -0.06
    �
    -0.06
     guarantee
    -0.06
     bonne
    -0.06
     희
    -0.06
    指导
    -0.06
    642
    -0.05
    POSITIVE LOGITS
    (integer
    0.07
    ,application
    0.07
    arrass
    0.07
     staging
    0.07
     geil
    0.07
    ність
    0.06
     shaped
    0.06
     tornado
    0.06
    Founded
    0.06
     mysqli
    0.06
    Act Density 0.285%

    No Known Activations