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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eci
    -0.07
    먜
    -0.07
     מצ
    -0.07
     hostility
    -0.07
     Transition
    -0.07
    갚
    -0.07
    缞
    -0.07
     Partnership
    -0.07
    cession
    -0.07
     넘
    -0.07
    POSITIVE LOGITS
    wing
    0.07
     WHEN
    0.07
     qDebug
    0.07
     scen
    0.07
    爺
    0.07
    渣
    0.07
     gente
    0.07
    }>{
    0.07
    	when
    0.06
    手腕
    0.06
    Act Density 0.012%

    No Known Activations