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

    Neuronpedia

    INDEX
    Explanations

    English and Hindi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.55
    s
    0.51
    ić
    0.50
     チ
    0.50
    ي
    0.49
    lą
    0.49
     teléfonos
    0.49
    inac
    0.48
    čit
    0.48
    ruth
    0.47
    POSITIVE LOGITS
     আত্ম
    0.45
    摘要
    0.44
    自
    0.43
    творення
    0.42
     الصف
    0.41
    媺
    0.40
    响应
    0.40
    Responses
    0.40
     فهي
    0.40
    逐
    0.40
    Act Density 0.001%

    No Known Activations