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

    Neuronpedia

    INDEX
    Explanations

    size and automatic processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     warna
    1.34
     SGS
    1.33
    Dreams
    1.31
     effet
    1.30
    raltar
    1.30
     EMP
    1.29
    idée
    1.29
    metals
    1.27
     Probe
    1.27
    Probe
    1.27
    POSITIVE LOGITS
    t
    1.91
    dır
    1.80
    et
    1.76
    es
    1.73
    ਤ
    1.61
    i
    1.59
    u
    1.55
    it
    1.41
    st
    1.39
    is
    1.38
    Act Density 0.001%

    No Known Activations