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

    Neuronpedia

    INDEX
    Explanations

    sentiments or Croatian forces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Interference
    0.55
    ನು
    0.47
    чого
    0.46
     trivalent
    0.46
     Countess
    0.46
    している
    0.46
     silencing
    0.45
    лож
    0.44
     Localization
    0.44
     Differentiation
    0.44
    POSITIVE LOGITS
    funktion
    0.47
     oyunc
    0.46
    flo
    0.45
    fabric
    0.45
     ফ্লাই
    0.45
    iconfont
    0.45
     বেড়ে
    0.43
     verbunden
    0.43
     ausgew
    0.42
    bytecode
    0.41
    Act Density 0.001%

    No Known Activations