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

    Neuronpedia

    INDEX
    Explanations

    Heidelberg University Oncology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Flush
    0.42
     قطر
    0.42
     Lincolnshire
    0.38
    Florida
    0.38
     feedwater
    0.38
     Lew
    0.37
     মুম্ব
    0.37
     puas
    0.37
     Stow
    0.37
    Twe
    0.37
    POSITIVE LOGITS
     Heidelberg
    0.67
     neck
    0.61
    Neck
    0.60
     Neck
    0.59
    Romantic
    0.54
    颈
    0.52
     Romantic
    0.52
    浪漫
    0.50
     romantic
    0.49
    idelberg
    0.48
    Act Density 0.002%

    No Known Activations