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

    Neuronpedia

    INDEX
    Explanations

    Code-related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !!!!
    -0.07
     productivity
    -0.07
    摩托
    -0.07
    ὅ
    -0.07
    óc
    -0.07
    猪肉
    -0.06
    小米
    -0.06
    ­ing
    -0.06
     falsely
    -0.06
     vulgar
    -0.06
    POSITIVE LOGITS
     goal
    0.07
     Caf
    0.07
     prob
    0.07
    进展情况
    0.07
    的事情
    0.07
    ategy
    0.06
    .Ptr
    0.06
     spec
    0.06
    ⚃
    0.06
    SN
    0.06
    Act Density 0.002%

    No Known Activations