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

    Neuronpedia

    INDEX
    Explanations

    reason

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ORMAT
    -0.06
    ói
    -0.06
     conexión
    -0.06
     прям
    -0.06
    HashSet
    -0.06
    ıştır
    -0.06
     McCabe
    -0.06
    �
    -0.06
     ebp
    -0.06
    getPost
    -0.06
    POSITIVE LOGITS
    bron
    0.08
     manner
    0.06
    梦
    0.06
     beard
    0.06
    Res
    0.06
     AIDS
    0.06
    thesis
    0.06
    ΙΚ
    0.06
    -elected
    0.06
    vements
    0.06
    Act Density 0.079%

    No Known Activations