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

    Neuronpedia

    INDEX
    Explanations

    varied text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    osoba
    -0.55
     Plume
    -0.52
     BaseModel
    -0.51
    expandindo
    -0.51
    '
    -0.50
    Continu
    -0.50
    Hentet
    -0.49
    iov
    -0.49
    améliorer
    -0.48
     kasarigan
    -0.47
    POSITIVE LOGITS
    اریخ
    0.59
     ainfi
    0.52
    Rhestr
    0.49
    fjspx
    0.49
    HAVE
    0.48
    MLLoader
    0.46
    ünsche
    0.46
     eorum
    0.46
     dirait
    0.45
     cardíaca
    0.45
    Act Density 0.032%

    No Known Activations