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

    Neuronpedia

    INDEX
    Explanations

    product descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /profile
    -0.06
     plaintiff
    -0.06
    >P
    -0.06
    ‌
    -0.06
    θούν
    -0.06
    َم
    -0.06
     newcomers
    -0.05
    �
    -0.05
     salads
    -0.05
    ायद
    -0.05
    POSITIVE LOGITS
     carousel
    0.07
     která
    0.07
     NSS
    0.07
    (lock
    0.07
    .bootstrap
    0.07
     chắn
    0.07
     bara
    0.06
     lh
    0.06
    だが
    0.06
     siguiente
    0.06
    Act Density 0.131%

    No Known Activations