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

    Neuronpedia

    INDEX
    Explanations

    advanced technologies and devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hibits
    -0.80
     камен
    -0.75
     positives
    -0.75
    ɽ
    -0.75
    mmm
    -0.75
     Gautier
    -0.75
    ฏ
    -0.73
     Pasir
    -0.73
    corre
    -0.72
     Sungai
    -0.72
    POSITIVE LOGITS
    ilingual
    0.84
     flüs
    0.81
     threes
    0.79
    eaways
    0.77
    commodations
    0.76
    軽い
    0.75
     sows
    0.75
     Brou
    0.75
     technolog
    0.74
    lanie
    0.74
    Act Density 0.036%

    No Known Activations