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

    Neuronpedia

    INDEX
    Explanations

    200

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trải
    -0.07
     anomaly
    -0.06
    _al
    -0.06
    �
    -0.06
    uffling
    -0.06
     imperial
    -0.06
     methodName
    -0.06
     vanity
    -0.06
    .MEDIA
    -0.06
    bindParam
    -0.06
    POSITIVE LOGITS
    ,buf
    0.07
     LAB
    0.07
    ========↵
    0.07
     RATE
    0.06
    .ru
    0.06
     Rout
    0.06
     MAP
    0.06
    егра
    0.06
    _encode
    0.06
    족
    0.06
    Act Density 0.004%

    No Known Activations