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

    Neuronpedia

    INDEX
    Explanations

    more details or sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CFR
    0.40
    กับการ
    0.38
     CHAN
    0.37
     EBS
    0.37
    َال
    0.36
     DEA
    0.35
     gobern
    0.35
     Jeopardy
    0.35
     adjournment
    0.34
     inadequ
    0.33
    POSITIVE LOGITS
    Hola
    0.42
    Show
    0.40
    description
    0.39
     그럼
    0.38
    একদিন
    0.38
    ura
    0.37
    }
    0.37
    Button
    0.37
     resumen
    0.37
    𝚕
    0.37
    Act Density 0.000%

    No Known Activations