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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cycl
    -0.07
    Ops
    -0.07
     Cycl
    -0.07
    {↵↵
    -0.06
    _G
    -0.06
     cryptocurrency
    -0.06
     Pf
    -0.06
    Online
    -0.06
    GW
    -0.06
    xFFF
    -0.06
    POSITIVE LOGITS
     поруш
    0.07
     decode
    0.07
    Sprite
    0.06
     лише
    0.06
    .test
    0.06
     Salisbury
    0.06
    からの
    0.06
     vlast
    0.06
     según
    0.06
    ранения
    0.06
    Act Density 0.053%

    No Known Activations