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

    Neuronpedia

    INDEX
    Explanations

    character descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yere
    -0.06
     FormData
    -0.06
     responder
    -0.06
    .bin
    -0.06
     HBO
    -0.06
     Sm
    -0.06
    fi
    -0.06
     bardzo
    -0.06
     Pence
    -0.06
     Xml
    -0.06
    POSITIVE LOGITS
    .Branch
    0.07
    Serve
    0.07
    (track
    0.07
    !
    0.06
     getImage
    0.06
     Upon
    0.06
    idak
    0.06
    stasy
    0.06
    ench
    0.06
     �
    0.06
    Act Density 0.074%

    No Known Activations