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

    Neuronpedia

    INDEX
    Explanations

    chemical reactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     notified
    -0.08
    れます
    -0.07
     Ben
    -0.07
    изации
    -0.07
    imization
    -0.07
    𬬻
    -0.07
    vero
    -0.07
    앙
    -0.07
    なので
    -0.07
     Legislature
    -0.07
    POSITIVE LOGITS
     electroly
    0.07
    쏟
    0.07
     cerv
    0.07
    '][]
    0.07
     Surv
    0.07
    ="
    0.07
     жид
    0.07
    ออนไล
    0.07
     assass
    0.07
    眷
    0.07
    Act Density 0.043%

    No Known Activations