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

    Neuronpedia

    INDEX
    Explanations

    school

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hey
    -0.07
     repo
    -0.07
    Convert
    -0.06
    unix
    -0.06
    please
    -0.06
     счита
    -0.06
     scientists
    -0.06
     кирп
    -0.06
     CEO
    -0.06
    しかし
    -0.06
    POSITIVE LOGITS
    追
    0.07
     TAX
    0.07
    106
    0.07
     invoked
    0.06
    abbix
    0.06
    Mitch
    0.06
     economical
    0.06
    四
    0.06
     inev
    0.06
     posix
    0.06
    Act Density 0.016%

    No Known Activations