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

    Neuronpedia

    INDEX
    Explanations

    Agreements, United States

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ppl
    -0.07
     obviously
    -0.06
     nuova
    -0.06
    information
    -0.06
    Spread
    -0.06
     Diploma
    -0.06
    Pow
    -0.06
     NEW
    -0.06
     "\↵
    -0.06
    sql
    -0.06
    POSITIVE LOGITS
    ockey
    0.07
     outings
    0.06
    ddit
    0.06
    /{}/
    0.06
    .predict
    0.06
    onomic
    0.06
    antics
    0.06
     인터
    0.06
     RET
    0.06
    ]';↵
    0.06
    Act Density 0.003%

    No Known Activations