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

    Neuronpedia

    INDEX
    Explanations

    science math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    禮
    -0.08
    /security
    -0.07
    _)
    -0.07
     từng
    -0.06
     Eleanor
    -0.06
     관련
    -0.06
    256
    -0.06
    /lgpl
    -0.06
    ('.')↵
    -0.06
     사무
    -0.06
    POSITIVE LOGITS
     Logic
    0.06
    áln
    0.06
    .sp
    0.06
    unding
    0.06
     leaving
    0.06
     endowed
    0.06
     icy
    0.06
    Mark
    0.06
    ..."↵
    0.06
                    ↵                ↵
    0.06
    Act Density 0.039%

    No Known Activations