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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Substring
    -0.07
    "]:↵
    -0.07
    $field
    -0.07
    .Mutex
    -0.06
    -fontawesome
    -0.06
     countryCode
    -0.06
    ]['
    -0.06
    orient
    -0.06
     esac
    -0.06
    Nut
    -0.06
    POSITIVE LOGITS
     inhib
    0.07
     gaz
    0.06
     एड
    0.06
    ностью
    0.06
    /support
    0.06
     dB
    0.06
    ือก
    0.06
     interv
    0.06
     +(
    0.06
     extra
    0.06
    Act Density 0.016%

    No Known Activations