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

    Neuronpedia

    INDEX
    Explanations

    Troubleshooting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .soft
    -0.07
    unidad
    -0.07
     Tomato
    -0.06
    ходит
    -0.06
    adan
    -0.06
     bilgisayar
    -0.06
     METHODS
    -0.06
     luxurious
    -0.06
    jump
    -0.06
    Completed
    -0.06
    POSITIVE LOGITS
    [i
    0.07
    減
    0.07
    -under
    0.07
    !*\↵
    0.06
     žen
    0.06
    (Entity
    0.06
     Δή
    0.06
    .Struct
    0.06
     Items
    0.06
     corporation
    0.06
    Act Density 0.021%

    No Known Activations