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

    Neuronpedia

    INDEX
    Explanations

    arguments and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     capire
    0.47
    Ф
    0.47
    Chat
    0.46
    Почему
    0.46
    qp
    0.46
    ्वा
    0.45
     Ф
    0.45
     wondering
    0.44
    zx
    0.44
    یس
    0.44
    POSITIVE LOGITS
    పురం
    0.55
    ής
    0.54
    asambhavam
    0.48
    ដ្ឋ
    0.48
    かる
    0.47
    estellten
    0.45
     magnolia
    0.43
     Mughal
    0.43
     Ventil
    0.42
     εφαρμο
    0.42
    Act Density 0.000%

    No Known Activations