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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cury
    -0.07
    消费需求
    -0.07
     particles
    -0.07
    同心
    -0.07
    글
    -0.06
     Replica
    -0.06
    ül
    -0.06
    "This
    -0.06
     Speed
    -0.06
     absorption
    -0.06
    POSITIVE LOGITS
     #-
    0.09
    Regex
    0.07
     Natalie
    0.07
     zipfile
    0.07
    📃
    0.07
    /animate
    0.07
    .none
    0.07
    (tr
    0.07
    .Assign
    0.07
     למשל
    0.07
    Act Density 0.016%

    No Known Activations