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

    Neuronpedia

    INDEX
    Explanations

    programming/technical issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vrij
    -0.07
     Cameroon
    -0.07
    빛
    -0.07
    했던
    -0.07
     पड
    -0.07
     formally
    -0.06
     Unfortunately
    -0.06
    ولو
    -0.06
    amb
    -0.06
     parody
    -0.06
    POSITIVE LOGITS
     />;↵
    0.07
     teleport
    0.06
    {}{↵
    0.06
     specialty
    0.06
    ITED
    0.06
     )
↵
    0.06
    charAt
    0.06
    "]:↵
    0.06
    ']↵
    0.06
    ้↵
    0.06
    Act Density 0.000%

    No Known Activations