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

    Neuronpedia

    INDEX
    Explanations

    numbers around 200

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     syntax
    -0.07
    attended
    -0.06
    anager
    -0.06
    geom
    -0.06
     Steel
    -0.06
     Growth
    -0.06
     Planner
    -0.06
    -court
    -0.06
    -art
    -0.06
    scription
    -0.06
    POSITIVE LOGITS
     становить
    0.07
    fullname
    0.07
     infinite
    0.07
    835
    0.07
    getNode
    0.06
    angkan
    0.06
    malloc
    0.06
    ุคคล
    0.06
    accounts
    0.06
    		↵	↵
    0.06
    Act Density 0.049%

    No Known Activations