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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }}/
    -0.07
    lectual
    -0.07
    uem
    -0.06
    klä
    -0.06
    _Local
    -0.06
    getClass
    -0.06
    뮤
    -0.06
    디
    -0.06
    mount
    -0.06
    LOSS
    -0.06
    POSITIVE LOGITS
     Elig
    0.07
     Moore
    0.07
     companions
    0.07
     Larson
    0.06
    agram
    0.06
    €™
    0.06
     wished
    0.06
    Newton
    0.06
     Nexus
    0.06
     Valerie
    0.06
    Act Density 0.000%

    No Known Activations