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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /T
    -0.07
    …↵↵↵↵
    -0.07
    ;

↵
    -0.07
    }

↵
    -0.06
     //
↵
↵
    -0.06
     {

↵
    -0.06
    //---------------------------------------------------------------------------↵
    -0.06
     setUsername
    -0.06
    LOUD
    -0.06
    .*;↵↵
    -0.06
    POSITIVE LOGITS
    -description
    0.07
    ３
    0.06
    FlatButton
    0.06
     위해
    0.06
     Photographer
    0.06
    quez
    0.06
     salaries
    0.06
     �
    0.06
    Qual
    0.06
    ตรว
    0.06
    Act Density 0.415%

    No Known Activations