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

    Neuronpedia

    INDEX
    Explanations

    regret

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tidy
    -0.06
     blanco
    -0.06
     insanların
    -0.06
    (Customer
    -0.06
     Heavenly
    -0.06
     invisible
    -0.06
     safe
    -0.06
    Hospital
    -0.06
     dove
    -0.06
     ninh
    -0.06
    POSITIVE LOGITS
     regret
    0.19
     regrets
    0.16
    icies
    0.07
    tel
    0.07
    _expire
    0.06
     RET
    0.06
    .rand
    0.06
    役
    0.06
    وگر
    0.06
     prematurely
    0.06
    Act Density 0.002%

    No Known Activations