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

    Neuronpedia

    INDEX
    Explanations

    code comments and logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Z
    0.52
     Bible
    0.46
    。
    0.45
     beantwort
    0.45
     Valley
    0.44
     Baby
    0.44
     stunned
    0.43
     Sweet
    0.42
     OCD
    0.42
     Fine
    0.42
    POSITIVE LOGITS
    뭄
    0.50
    鹈
    0.49
    Idioma
    0.49
    יל
    0.49
    slotBox
    0.48
    તુ
    0.46
     estable
    0.46
     pošt
    0.46
    ătur
    0.44
    膊
    0.44
    Act Density 0.000%

    No Known Activations