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

    Neuronpedia

    INDEX
    Explanations

    symbols and specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utiliz
    0.38
     permission
    0.37
     utilizza
    0.36
    imagenes
    0.36
     Along
    0.35
    দ্রোহ
    0.35
     utiliser
    0.35
     miss
    0.34
     Videos
    0.34
     fus
    0.34
    POSITIVE LOGITS
     жөн
    0.45
    恣
    0.43
    ingleton
    0.42
    示
    0.41
    nać
    0.40
    𐰴
    0.40
     వే
    0.40
     вол
    0.40
    ewód
    0.40
    ⃣
    0.40
    Act Density 0.000%

    No Known Activations