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

    Neuronpedia

    INDEX
    Explanations

    API levels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wired
    -0.07
    )));
↵
    -0.07
    лагод
    -0.06
    福
    -0.06
     suppression
    -0.06
    Telephone
    -0.06
    に入
    -0.06
     deux
    -0.06
    _PAGE
    -0.06
    boards
    -0.06
    POSITIVE LOGITS
    testdata
    0.07
    Segoe
    0.07
     Tyr
    0.07
     whole
    0.07
     соверш
    0.07
     %%
    0.06
     groß
    0.06
     گرد
    0.06
    .labelControl
    0.06
     quar
    0.06
    Act Density 0.004%

    No Known Activations