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

    Neuronpedia

    INDEX
    Explanations

    News articles with names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -validator
    -0.06
     python
    -0.06
     Isl
    -0.06
    ेदन
    -0.06
    550
    -0.06
    shaw
    -0.06
     clique
    -0.06
    _SERIAL
    -0.06
    Switch
    -0.06
     tuner
    -0.06
    POSITIVE LOGITS
     alleged
    0.07
    .deck
    0.07
    erule
    0.06
    Unavailable
    0.06
    aleb
    0.06
    ırlar
    0.06
    )');↵
    0.06
     note
    0.06
     materi
    0.06
     agli
    0.06
    Act Density 0.022%

    No Known Activations