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
    リスト
    -0.08
     helpless
    -0.07
    |\
    -0.07
    álních
    -0.06
    قی
    -0.06
    uing
    -0.06
     empty
    -0.06
    —which
    -0.06
    atoi
    -0.06
     Prescription
    -0.06
    POSITIVE LOGITS
     ContentType
    0.06
    747
    0.06
     MyApp
    0.06
     kf
    0.06
    -get
    0.06
     steals
    0.06
    <Vertex
    0.06
     rentals
    0.06
     bef
    0.06
     сх
    0.06
    Act Density 0.039%

    No Known Activations