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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    operator
    -0.07
    Official
    -0.07
    >User
    -0.07
    Trade
    -0.06
     ihr
    -0.06
     WRONG
    -0.06
    (el
    -0.06
     เด
    -0.06
     Myanmar
    -0.06
    .Decode
    -0.06
    POSITIVE LOGITS
    .false
    0.06
     shalt
    0.06
     продук
    0.06
     چشم
    0.06
    .dynamic
    0.06
    /loader
    0.06
    /gtest
    0.06
     감
    0.06
    ��取
    0.06
    .rt
    0.06
    Act Density 0.303%

    No Known Activations