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

    Neuronpedia

    INDEX
    Explanations

    Russian

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()],
    -0.07
    Lock
    -0.07
     di
    -0.07
    .org
    -0.07
    INI
    -0.06
    执行
    -0.06
     Ι
    -0.06
    irling
    -0.06
     parks
    -0.06
    ιώ
    -0.06
    POSITIVE LOGITS
     inoc
    0.07
     сна
    0.07
     miscar
    0.07
     Хар
    0.07
     Healthy
    0.06
     diet
    0.06
    Chair
    0.06
     нат
    0.06
     augment
    0.06
     bladder
    0.06
    Act Density 0.006%

    No Known Activations