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

    Neuronpedia

    INDEX
    Explanations

    Understanding or misunderstanding messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wl
    -0.08
     tiếng
    -0.07
    iore
    -0.07
     Warner
    -0.06
     wides
    -0.06
     fish
    -0.06
    кие
    -0.06
    isher
    -0.06
    :L
    -0.06
    _pas
    -0.06
    POSITIVE LOGITS
     εφαρ
    0.06
    Lord
    0.06
     Chrysler
    0.06
     �
    0.06
     ETA
    0.06
     deter
    0.06
     Jedi
    0.06
    \Web
    0.06
     vzpom
    0.06
     plastics
    0.06
    Act Density 0.039%

    No Known Activations