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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '**
    -0.07
     robbery
    -0.07
    _jet
    -0.07
    .sg
    -0.07
    .perform
    -0.07
     projektu
    -0.07
    ए
    -0.07
     yapılan
    -0.06
    기를
    -0.06
    ัตน
    -0.06
    POSITIVE LOGITS
    coli
    0.07
     conjug
    0.06
    S
    0.06
    嗯
    0.06
     arbe
    0.06
        ↵↵
    0.06
     پایان
    0.06
    cerpt
    0.06
    Scient
    0.06
     solidity
    0.06
    Act Density 0.021%

    No Known Activations