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

    Neuronpedia

    INDEX
    Explanations

    acronyms or coded language referring to websites, ships, or scientific study

    oai_token-act-pair · gemini-2.0-flash

    space, ship

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ship
    -1.92
    s
    -1.66
    school
    -1.66
    space
    -1.63
    shop
    -1.62
    systems
    -1.59
    solutions
    -1.55
    sing
    -1.55
    soft
    -1.55
    ski
    -1.54
    POSITIVE LOGITS
     s
    0.84
    S
    0.72
    Sj
    0.63
     س
    0.61
    ss
    0.60
    Ｓ
    0.59
     S
    0.58
     Sot
    0.57
    si
    0.57
     sb
    0.57
    Act Density 4.020%

    No Known Activations