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

    Neuronpedia

    INDEX
    Explanations

    Comcast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cáo
    -0.07
    219
    -0.07
     &
    -0.06
    erved
    -0.06
     UV
    -0.06
    mon
    -0.06
    examples
    -0.06
    身
    -0.06
    -method
    -0.06
    ategorias
    -0.06
    POSITIVE LOGITS
     Comcast
    0.17
     Transformer
    0.16
     McConnell
    0.14
     Schl
    0.13
     hostel
    0.13
     banc
    0.08
     Bosnia
    0.08
     schl
    0.08
    Connell
    0.07
    OneToMany
    0.07
    Act Density 0.003%

    No Known Activations