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

    Neuronpedia

    INDEX
    Explanations

    court documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дерев
    -0.06
    971
    -0.06
    olulu
    -0.06
     grasp
    -0.06
    毛
    -0.06
    Reduc
    -0.06
     Armenian
    -0.06
     ocur
    -0.06
    nictví
    -0.06
     ран
    -0.06
    POSITIVE LOGITS
    練
    0.08
    atched
    0.08
    OUNTRY
    0.07
     nameLabel
    0.07
     complied
    0.06
     initialValue
    0.06
     Similar
    0.06
    PBS
    0.06
     FIRST
    0.06
    ike
    0.06
    Act Density 0.002%

    No Known Activations