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

    Neuronpedia

    INDEX
    Explanations

    Sports qualifications and quotas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    يكي
    -0.07
    .ndim
    -0.07
    ,(
    -0.06
     esper
    -0.06
    EG
    -0.06
     entreg
    -0.06
    čen
    -0.06
     pozn
    -0.06
    Wel
    -0.06
    sv
    -0.06
    POSITIVE LOGITS
     Roads
    0.08
    //↵↵↵
    0.07
     murderers
    0.07
    /stdc
    0.06
     differential
    0.06
    Network
    0.06
    <pcl
    0.06
     executive
    0.06
    eventType
    0.06
     designated
    0.06
    Act Density 0.000%

    No Known Activations