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

    Neuronpedia

    INDEX
    Explanations

    Lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     каф
    -0.07
     그러나
    -0.07
     rew
    -0.07
    改
    -0.07
    очно
    -0.07
     стен
    -0.06
     sq
    -0.06
     holster
    -0.06
     неб
    -0.06
    ambda
    -0.06
    POSITIVE LOGITS
    .Editor
    0.07
     depth
    0.06
    Calendar
    0.06
     ‐
    0.06
    -da
    0.06
    .bam
    0.06
     Mehmet
    0.06
    (dev
    0.06
    -xl
    0.05
    общ
    0.05
    Act Density 0.115%

    No Known Activations