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

    Neuronpedia

    INDEX
    Explanations

    write commands and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ami
    0.46
    Fill
    0.45
    ft
    0.40
    o
    0.40
     chicas
    0.39
    si
    0.38
     hid
    0.38
    ia
    0.38
     implemented
    0.38
     autom
    0.38
    POSITIVE LOGITS
    ᆢ
    0.52
     revising
    0.46
    revise
    0.46
     palindrome
    0.46
     chronology
    0.45
     revise
    0.45
     Evidently
    0.44
    刋
    0.44
     revised
    0.44
    ীন্দ্র
    0.44
    Act Density 0.000%

    No Known Activations