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

    Neuronpedia

    INDEX
    Explanations

    Insurance policies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ayında
    -0.07
    postgresql
    -0.07
    aims
    -0.06
    (room
    -0.06
    IX
    -0.06
     освіти
    -0.06
     акти
    -0.06
     reunited
    -0.06
    composite
    -0.06
    (agent
    -0.06
    POSITIVE LOGITS
     rtrim
    0.07
     б
    0.07
    .Quad
    0.07
     đ
    0.07
     SPEED
    0.06
    maj
    0.06
    jec
    0.06
    ๆ
    0.06
     giveaways
    0.06
    elem
    0.06
    Act Density 0.022%

    No Known Activations