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

    Neuronpedia

    INDEX
    Explanations

    my

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     occurring
    -0.08
    采用
    -0.07
     OR
    -0.07
    349
    -0.07
    ystone
    -0.07
     borough
    -0.07
     occur
    -0.07
     Major
    -0.07
     plane
    -0.07
    izada
    -0.06
    POSITIVE LOGITS
    ie
    0.13
     Eddie
    0.12
     Jimmy
    0.11
    mie
    0.10
     Johnny
    0.09
     Tommy
    0.09
     Charlie
    0.09
    IE
    0.09
    Johnny
    0.09
    ddie
    0.09
    Act Density 0.043%

    No Known Activations