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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    눞
    -0.07
     allow
    -0.07
    Beer
    -0.07
    听众
    -0.07
    承包
    -0.07
    **:
    -0.07
    II
    -0.07
    ites
    -0.07
     Nach
    -0.07
    bió
    -0.06
    POSITIVE LOGITS
    .lot
    0.07
    _js
    0.07
     washington
    0.07
    _Reg
    0.07
    .enterprise
    0.07
     transition
    0.07
     genomic
    0.07
     raced
    0.06
     находится
    0.06
     rotated
    0.06
    Act Density 0.014%

    No Known Activations