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

    Neuronpedia

    INDEX
    Explanations

    programming code fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    した
    0.59
    について
    0.52
     denke
    0.52
     ges
    0.50
     JPA
    0.50
    ://
    0.50
     niz
    0.49
    ｎ
    0.49
    ",
    0.47
     savvy
    0.47
    POSITIVE LOGITS
    kec
    0.50
    0.50
    piano
    0.49
    GNU
    0.48
     கட்டப்பட்டது
    0.48
    ﺔ
    0.48
    nte
    0.47
     சிகி
    0.47
    kami
    0.46
    르
    0.46
    Act Density 0.000%

    No Known Activations