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

    Neuronpedia

    INDEX
    Explanations

    published

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _estado
    -0.07
     Citizenship
    -0.06
     realized
    -0.06
     Blades
    -0.06
     Allowed
    -0.06
     TAR
    -0.06
     nya
    -0.06
    Hey
    -0.06
     stubborn
    -0.06
    (enabled
    -0.06
    POSITIVE LOGITS
     proficient
    0.07
     incredible
    0.07
     Compiler
    0.06
     клад
    0.06
    deck
    0.06
     Errors
    0.06
     Companies
    0.06
    upy
    0.06
    ron
    0.06
    published
    0.06
    Act Density 0.001%

    No Known Activations