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
     flex
    -0.06
    ----
    -0.06
    rets
    -0.06
    cred
    -0.06
    thes
    -0.06
     HttpHeaders
    -0.06
    omedical
    -0.06
    \xa
    -0.06
     dez
    -0.06
    mant
    -0.06
    POSITIVE LOGITS
    ラン
    0.09
     كان
    0.07
    _scal
    0.07
     totiž
    0.07
    ام
    0.07
     ak
    0.07
     NSArray
    0.07
     |
    0.07
     순
    0.07
    _pix
    0.07
    Act Density 0.018%

    No Known Activations