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

    Neuronpedia

    INDEX
    Explanations

    hazards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    统计
    -0.07
    pei
    -0.07
     municipal
    -0.06
     Wikipedia
    -0.06
    рен
    -0.06
    卒
    -0.06
     Παν
    -0.06
     unanimously
    -0.06
     triangle
    -0.06
     Από
    -0.06
    POSITIVE LOGITS
             
↵
    0.07
     lumber
    0.06
    Since
    0.06
    ELS
    0.06
    NAME
    0.06
    μ
    0.06
    Hibernate
    0.06
    hack
    0.06
     cognition
    0.06
    THING
    0.06
    Act Density 0.000%

    No Known Activations