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
     attitude
    -0.06
    Streaming
    -0.06
     ge
    -0.06
     Lion
    -0.06
     Eduardo
    -0.06
     touchdowns
    -0.06
     Croatian
    -0.06
     MES
    -0.06
     Geoffrey
    -0.05
    >|
    -0.05
    POSITIVE LOGITS
     jak
    0.07
    -animate
    0.07
    .Call
    0.07
     保
    0.06
    ерж
    0.06
     Fixes
    0.06
    аксим
    0.06
     tribes
    0.06
    قال
    0.06
     hiking
    0.06
    Act Density 0.114%

    No Known Activations