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

    Neuronpedia

    INDEX
    Explanations

    mit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mitchell
    -0.84
     mit
    -0.82
    Mitchell
    -0.73
     Morris
    -0.68
    operative
    -0.64
     MITCHELL
    -0.58
    mekte
    -0.50
    Források
    -0.50
     que
    -0.50
    addComponent
    -0.50
    POSITIVE LOGITS
     Shakspeare
    0.84
    ſelf
    0.77
     myſelf
    0.75
     Majefty
    0.74
     Efq
    0.74
     Jefus
    0.70
     themſelves
    0.70
     houſe
    0.68
    ſelves
    0.67
     ſtate
    0.66
    Act Density 0.169%

    No Known Activations