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

    Neuronpedia

    INDEX
    Explanations

    encourage our, of value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    es
    0.57
    u
    0.57
    ad
    0.57
    ost
    0.57
    er
    0.54
    ach
    0.54
    cache
    0.53
    ato
    0.52
    an
    0.51
    kiss
    0.51
    POSITIVE LOGITS
    融入
    0.61
    吓
    0.59
    乐
    0.55
    展览
    0.54
    个
    0.54
    飞行
    0.54
     párrafo
    0.53
    しておく
    0.53
    ManagerPortal
    0.53
    院
    0.52
    Act Density 0.000%

    No Known Activations