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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sampler
    -0.07
     CET
    -0.06
     Thy
    -0.06
    ichern
    -0.06
     адміністра
    -0.06
     agreement
    -0.06
    聚
    -0.06
     connects
    -0.06
     Hem
    -0.06
    andan
    -0.06
    POSITIVE LOGITS
    пол
    0.07
     fearless
    0.07
     speculated
    0.06
     krát
    0.06
     pomoc
    0.06
    _LINK
    0.06
     physicist
    0.06
    .Click
    0.06
    '=
    0.06
    repid
    0.06
    Act Density 0.033%

    No Known Activations