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

    Neuronpedia

    INDEX
    Explanations

    zealous, recognizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝒚
    0.92
     aficionados
    0.82
    ə
    0.80
    XmlElement
    0.78
    MovieModal
    0.75
    서
    0.75
     beragam
    0.74
     professionals
    0.73
     profesionales
    0.73
     persevere
    0.72
    POSITIVE LOGITS
    ။
    0.78
     उसने
    0.75
    <0x92>
    0.69
     установки
    0.69
    hardness
    0.69
    畔
    0.69
     turbidity
    0.67
    druck
    0.66
     सॉ
    0.66
    하다
    0.66
    Act Density 0.000%

    No Known Activations