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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出去
    -0.08
     chiropr
    -0.07
    ным
    -0.07
     Israelis
    -0.07
     접근
    -0.07
    ⚚
    -0.06
    Police
    -0.06
     iov
    -0.06
    亸
    -0.06
    قوم
    -0.06
    POSITIVE LOGITS
     honoring
    0.07
    _si
    0.07
    	mp
    0.07
     useRouter
    0.07
    による
    0.07
     Wikipedia
    0.06
    .rad
    0.06
    /pr
    0.06
    _cond
    0.06
     unjust
    0.06
    Act Density 0.000%

    No Known Activations