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

    Neuronpedia

    INDEX
    Explanations

    song titles and lyrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.40
     Which
    0.39
     tom
    0.38
     società
    0.37
    垻
    0.36
     Trade
    0.36
    䍩
    0.35
     oltre
    0.35
     Nutrition
    0.34
     Software
    0.34
    POSITIVE LOGITS
    🔈
    0.41
    DropDownList
    0.41
     בת
    0.40
     అయితే
    0.39
     స్
    0.38
    🙏🙏
    0.38
    ო
    0.38
    💮
    0.38
     તમામ
    0.37
    Message
    0.37
    Act Density 0.001%

    No Known Activations