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

    Neuronpedia

    INDEX
    Explanations

    virtual introduction, processing, shapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hattim
    0.40
    nCurr
    0.39
    npj
    0.38
     katth
    0.37
    aprendizaje
    0.37
    🏛
    0.37
    ধরনের
    0.36
    anyol
    0.36
    innt
    0.36
    ANN
    0.36
    POSITIVE LOGITS
     [
    0.39
     住
    0.39
     disimpan
    0.36
     fixing
    0.34
    这里
    0.33
     photom
    0.33
    ্ভব
    0.33
     sitzt
    0.32
     Fix
    0.32
     لهم
    0.32
    Act Density 0.000%

    No Known Activations