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

    Neuronpedia

    INDEX
    Explanations

    phone and volume instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.64
    تهم
    0.56
    ت
    0.51
    т
    0.50
    ля
    0.49
    𝐠
    0.49
    y
    0.49
    7
    0.47
    ل
    0.47
    น
    0.47
    POSITIVE LOGITS
     to
    0.75
     prostitutes
    0.50
    】,
    0.49
     ɔ
    0.48
    Executives
    0.48
     〢
    0.47
     של
    0.47
     moſt
    0.47
     tropas
    0.46
     loudspeakers
    0.45
    Act Density 0.000%

    No Known Activations