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
    agnostics
    -0.07
    stí
    -0.07
     asia
    -0.07
    lix
    -0.07
    etics
    -0.07
    Hugh
    -0.06
     odense
    -0.06
     رمضان
    -0.06
    ções
    -0.06
     enhancements
    -0.06
    POSITIVE LOGITS
     DMA
    0.06
     $↵
    0.06
     Connor
    0.06
    Confirm
    0.06
     لد
    0.06
    様
    0.06
    ~":"
    0.06
     literal
    0.06
     LSD
    0.06
    _Msp
    0.06
    Act Density 0.073%

    No Known Activations