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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Seq
    -0.06
    .completed
    -0.06
     Challenges
    -0.06
     yoktur
    -0.06
     Sel
    -0.06
     osp
    -0.06
    olves
    -0.06
    armed
    -0.06
     zemí
    -0.06
     changing
    -0.06
    POSITIVE LOGITS
     України
    0.07
    .setType
    0.06
     например
    0.06
    ζα
    0.06
     Associates
    0.06
     İslam
    0.06
    �
    0.06
    damn
    0.06
    kills
    0.06
    ubo
    0.06
    Act Density 0.010%

    No Known Activations