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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     matcher
    -0.07
     repo
    -0.07
     مى
    -0.07
     meng
    -0.07
    ồng
    -0.07
     Ment
    -0.06
    (seg
    -0.06
     Rede
    -0.06
     Cru
    -0.06
    _my
    -0.06
    POSITIVE LOGITS
    筒
    0.06
     drifted
    0.06
     epidemi
    0.06
    succ
    0.06
     philosopher
    0.06
    ffee
    0.06
     Payload
    0.06
     oslo
    0.06
    oreferrer
    0.06
    .Require
    0.06
    Act Density 0.017%

    No Known Activations