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

    Neuronpedia

    INDEX
    Explanations

    box

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Direction
    -0.07
     peanuts
    -0.06
    .dst
    -0.06
     cyn
    -0.06
    azzo
    -0.06
    　イ
    -0.06
     contacto
    -0.06
     SUS
    -0.06
    (packet
    -0.06
     accuse
    -0.06
    POSITIVE LOGITS
     xmax
    0.07
    下来
    0.07
     Další
    0.06
     подключ
    0.06
     دارد
    0.06
     Mai
    0.06
     було
    0.06
     Prahy
    0.06
    dating
    0.06
     JSBracketAccess
    0.06
    Act Density 0.001%

    No Known Activations