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

    Neuronpedia

    INDEX
    Explanations

    Numerical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ่อย
    -0.07
    Tak
    -0.06
    cth
    -0.06
    Password
    -0.06
     Bush
    -0.06
     Warrior
    -0.06
    lista
    -0.06
    �
    -0.06
     �
    -0.06
     antioxid
    -0.05
    POSITIVE LOGITS
    <Map
    0.08
     Bradford
    0.07
    _processors
    0.07
    .submit
    0.06
     OWN
    0.06
     ------------
    0.06
     Sophia
    0.06
    ApplicationContext
    0.06
    "
↵
↵
↵
    0.06
    ưởng
    0.06
    Act Density 0.006%

    No Known Activations