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

    Neuronpedia

    INDEX
    Explanations

    stating opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orgt
    -0.06
    amel
    -0.06
    кін
    -0.06
    nant
    -0.06
     masc
    -0.06
    herits
    -0.06
    жди
    -0.06
    _revision
    -0.06
    agenda
    -0.06
     حکم
    -0.06
    POSITIVE LOGITS
    -expanded
    0.07
    Кон
    0.07
     believable
    0.07
    ]
↵
    0.07
     (!
    0.07
    \.
    0.07
    .Dialog
    0.06
    ////↵
    0.06
    .:
    0.06
    assuming
    0.06
    Act Density 0.130%

    No Known Activations