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

    Neuronpedia

    INDEX
    Explanations

    building something, trained to guide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ก
    0.52
     immig
    0.50
    ы
    0.50
     Ayl
    0.48
     proz
    0.48
    ñ
    0.48
    ğ
    0.48
     сюжет
    0.47
     cath
    0.46
     başta
    0.46
    POSITIVE LOGITS
    ッカー
    0.54
    <0x8C>
    0.50
    वू
    0.46
    udahkan
    0.45
    inds
    0.43
    ᠠ
    0.41
    icked
    0.41
    याम
    0.40
    ಾಗಿತ್ತು
    0.40
    六
    0.40
    Act Density 0.000%

    No Known Activations