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

    Neuronpedia

    INDEX
    Explanations

    code/technical explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eager
    -0.07
    ेह
    -0.07
     Tf
    -0.07
    erry
    -0.07
    ніч
    -0.06
    .set
    -0.06
    evt
    -0.06
     equipped
    -0.06
    estatus
    -0.06
    .dequeue
    -0.06
    POSITIVE LOGITS
    俺は
    0.06
     Yates
    0.06
    kenin
    0.06
     грун
    0.06
     derives
    0.06
     суспіль
    0.06
     WEB
    0.06
    ￣￣￣￣
    0.06
    □
    0.06
     yellow
    0.06
    Act Density 0.130%

    No Known Activations