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

    Neuronpedia

    INDEX
    Explanations

    .java

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     screens
    -0.07
     backgrounds
    -0.07
     stern
    -0.06
    %c
    -0.06
    ords
    -0.06
     reminiscent
    -0.06
    Arr
    -0.06
     درصد
    -0.06
     bec
    -0.06
    ;?>"
    -0.06
    POSITIVE LOGITS
    ляет
    0.07
     tweeting
    0.06
    berger
    0.06
    ψει
    0.06
    .md
    0.06
     Purple
    0.06
    ование
    0.06
    yper
    0.06
     exig
    0.06
    .AddListener
    0.06
    Act Density 0.009%

    No Known Activations