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

    Neuronpedia

    INDEX
    Explanations

    offers several

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    леду
    0.44
    GTUIKit
    0.44
    isVideoRecording
    0.43
    reflectionCamera
    0.42
    FIC
    0.42
     জিজ্ঞ
    0.42
    िवारी
    0.42
    quets
    0.42
     потра
    0.41
    lications
    0.41
    POSITIVE LOGITS
    k
    0.63
    s
    0.61
     to
    0.60
    st
    0.55
     Business
    0.54
     Just
    0.52
     Amount
    0.52
     S
    0.52
    iest
    0.50
     Absolutely
    0.50
    Act Density 0.000%

    No Known Activations