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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     capitalize
    -0.07
    (tmp
    -0.07
    ıf
    -0.06
    508
    -0.06
    .Relative
    -0.06
     EURO
    -0.06
     Donovan
    -0.06
     Tento
    -0.06
    pushViewController
    -0.06
    jících
    -0.06
    POSITIVE LOGITS
     برد
    0.07
    FER
    0.07
    fer
    0.06
     Unified
    0.06
     bapt
    0.06
     demanded
    0.06
    Authorized
    0.06
     weil
    0.06
     achievements
    0.06
    心
    0.06
    Act Density 0.013%

    No Known Activations