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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dimension
    -0.07
    身份证
    -0.07
     bson
    -0.07
     getResources
    -0.07
    躁
    -0.07
    /octet
    -0.06
    _many
    -0.06
     Oprah
    -0.06
     veterans
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     guideline
    0.07
     reel
    0.07
     còn
    0.07
    ела
    0.07
    OLS
    0.07
    _APP
    0.07
    בדק
    0.06
    :function
    0.06
    �
    0.06
     undead
    0.06
    Act Density 0.036%

    No Known Activations