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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smoothly
    -0.07
     faculty
    -0.07
    Select
    -0.07
     treasury
    -0.07
    department
    -0.07
     suburban
    -0.07
     Nir
    -0.06
     grids
    -0.06
     Science
    -0.06
     measures
    -0.06
    POSITIVE LOGITS
    astreet
    0.07
     улыб
    0.06
    (ViewGroup
    0.06
     千
    0.06
     verbally
    0.06
    strtolower
    0.06
    ्ध
    0.06
    れど
    0.06
    -fw
    0.06
    	Schema
    0.06
    Act Density 0.028%

    No Known Activations