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

    Neuronpedia

    INDEX
    Explanations

    hassle, need, load, stress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.88
     not
    0.61
    نی
    0.60
     itt
    0.57
    厘米
    0.57
     t
    0.55
     It
    0.55
    นี้
    0.55
     are
    0.54
    ते
    0.53
    POSITIVE LOGITS
     hassle
    0.63
    g
    0.62
     hassles
    0.60
     worry
    0.59
     worries
    0.59
    hass
    0.59
     needlessly
    0.59
    orry
    0.56
     һәм
    0.55
    ۽
    0.55
    Act Density 0.556%

    No Known Activations