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

    Neuronpedia

    INDEX
    Explanations

    ’s's from punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ラ
    0.41
     snar
    0.36
     WJ
    0.36
     wf
    0.36
    ทัน
    0.36
    𝙻
    0.35
     bulldog
    0.34
     tc
    0.34
    ร้าย
    0.33
     hark
    0.33
    POSITIVE LOGITS
     destes
    0.48
    jdbcType
    0.43
     Activated
    0.42
     centimetres
    0.42
    Como
    0.41
     Empresas
    0.41
     dosis
    0.40
    eksiyon
    0.40
     activa
    0.40
     hipótes
    0.40
    Act Density 0.073%

    No Known Activations