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

    Neuronpedia

    INDEX
    Explanations

    math/physics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erb
    -0.07
    .ico
    -0.07
    Ή
    -0.07
    ｐ
    -0.06
     раньше
    -0.06
     thaw
    -0.06
     rasp
    -0.06
    好奇心
    -0.06
     marginBottom
    -0.06
     alarmed
    -0.06
    POSITIVE LOGITS
    {name
    0.07
     canon
    0.07
    哪家好
    0.07
    _TIME
    0.07
    Hierarchy
    0.07
    jac
    0.07
    _roles
    0.06
    IsValid
    0.06
     deberá
    0.06
    的设计
    0.06
    Act Density 0.007%

    No Known Activations