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

    Neuronpedia

    INDEX
    Explanations

    comprises

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itat
    -0.08
    ünden
    -0.07
     vých
    -0.07
     sendo
    -0.07
    ič
    -0.07
    وك
    -0.07
    ycz
    -0.07
    iyon
    -0.07
    'il
    -0.07
    -animation
    -0.07
    POSITIVE LOGITS
     comprises
    0.07
    pt
    0.06
    ff
    0.06
     cortex
    0.06
     comprising
    0.06
     пог
    0.06
    .capture
    0.06
     пар
    0.06
     cascade
    0.06
     appendix
    0.06
    Act Density 0.004%

    No Known Activations