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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MBA
    -0.07
    谁都
    -0.07
     הכול
    -0.07
    習慣
    -0.07
    CREASE
    -0.07
    (strings
    -0.06
    退款
    -0.06
     MIL
    -0.06
    OUN
    -0.06
     Unicorn
    -0.06
    POSITIVE LOGITS
    imal
    0.07
    與
    0.06
    inus
    0.06
    舥
    0.06
    rxjs
    0.06
    与
    0.06
     thy
    0.06
    两点
    0.06
    走入
    0.06
    浛
    0.06
    Act Density 0.000%

    No Known Activations