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

    Neuronpedia

    INDEX
    Explanations

    against

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Chat
    -0.07
     producto
    -0.07
     Obs
    -0.07
     surrounding
    -0.07
     історії
    -0.07
    buy
    -0.07
    thumb
    -0.06
    .pass
    -0.06
    ٠
    -0.06
     cocktail
    -0.06
    POSITIVE LOGITS
     against
    0.12
     Against
    0.11
    against
    0.09
    Against
    0.08
    -important
    0.06
     onların
    0.06
    tering
    0.06
    allen
    0.06
    Confirmed
    0.06
    /／
    0.06
    Act Density 0.068%

    No Known Activations