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

    Neuronpedia

    INDEX
    Explanations

    Figure and Table references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cir
    -0.07
    broken
    -0.07
     worn
    -0.07
    holders
    -0.06
    비스
    -0.06
    (cors
    -0.06
    르는
    -0.06
     stringBuilder
    -0.06
     万元
    -0.06
    กระท
    -0.06
    POSITIVE LOGITS
    vect
    0.07
    Widget
    0.06
     Air
    0.06
    rink
    0.06
    -port
    0.06
      
    0.06
    :j
    0.06
     сок
    0.06
     porch
    0.06
     reads
    0.06
    Act Density 0.002%

    No Known Activations