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

    Neuronpedia

    INDEX
    Explanations

    limit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    476
    -0.08
    ười
    -0.07
     carro
    -0.07
    。あ
    -0.07
    cock
    -0.07
     Schro
    -0.07
    154
    -0.07
     vay
    -0.07
    あ
    -0.07
    /to
    -0.07
    POSITIVE LOGITS
     limit
    0.16
    Limit
    0.14
    limit
    0.14
     limits
    0.14
     Limit
    0.13
     lim
    0.13
     LIMIT
    0.12
    .limit
    0.12
    -limit
    0.12
     Limits
    0.12
    Act Density 0.035%

    No Known Activations