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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    League
    -0.07
    .Raise
    -0.07
    .raise
    -0.07
    _TRACK
    -0.07
    _management
    -0.07
     بعد
    -0.07
     Rahul
    -0.07
    回到
    -0.07
     quits
    -0.06
    Inlining
    -0.06
    POSITIVE LOGITS
    kat
    0.06
    ullan
    0.06
     paired
    0.06
    ResourceId
    0.06
    annes
    0.06
    (sockfd
    0.05
     ELF
    0.05
    _Move
    0.05
    anime
    0.05
    .faceVertexUvs
    0.05
    Act Density 0.046%

    No Known Activations