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

    Neuronpedia

    INDEX
    Explanations

    say "the ending Impl"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Рос
    -0.07
     stall
    -0.07
    よび
    -0.06
    -0.06
    arduino
    -0.06
     hinges
    -0.06
     Events
    -0.06
     fk
    -0.06
     yen
    -0.06
     bard
    -0.06
    POSITIVE LOGITS
    orgt
    0.08
    orsk
    0.07
    เสนอ
    0.06
     Phòng
    0.06
    aigned
    0.06
    NavigationView
    0.06
    udget
    0.06
     skating
    0.06
    ši
    0.06
    eurs
    0.06
    Act Density 0.009%

    No Known Activations