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

    Neuronpedia

    INDEX
    Explanations

    throws Exception types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused97>
    0.44
     }(\
    0.39
     }(
    0.38
    Forgery
    0.38
     gonflement
    0.38
     conteú
    0.37
    誤差
    0.37
     hemolytic
    0.36
     peritone
    0.36
    १८४
    0.36
    POSITIVE LOGITS
     Exception
    0.63
    Exception
    0.49
     Inter
    0.43
    Number
    0.42
     Number
    0.41
    argc
    0.40
     Throwable
    0.40
     an
    0.36
    tpl
    0.36
     Class
    0.35
    Act Density 0.004%

    No Known Activations