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

    Neuronpedia

    INDEX
    Explanations

    error and warning messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    衊
    0.41
    <0x92>
    0.39
    ttore
    0.38
    йын
    0.38
    ете
    0.37
    keen
    0.37
    eteer
    0.37
    คลิ
    0.37
    ាទ
    0.37
    ántico
    0.36
    POSITIVE LOGITS
    sanitize
    0.42
     حاول
    0.42
     hans
    0.42
     protestors
    0.40
     resized
    0.38
    اللي
    0.38
     api
    0.38
    San
    0.38
     bolster
    0.38
     Tul
    0.37
    Act Density 0.002%

    No Known Activations