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

    Neuronpedia

    INDEX
    Explanations

    formal titles and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.68
     on
    0.59
    >
    0.58
     lugares
    0.55
     preguntas
    0.55
    :"
    0.54
    td
    0.54
    When
    0.53
    :
    0.53
     placas
    0.53
    POSITIVE LOGITS
    नं
    0.68
    本机
    0.57
    น
    0.57
     自己
    0.55
     ಸ್ವ
    0.54
    ն
    0.54
     drows
    0.54
     पांडे
    0.53
    𝐧
    0.53
    禳
    0.51
    Act Density 0.000%

    No Known Activations