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

    Neuronpedia

    INDEX
    Explanations

    Suits and fires

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suit
    -1.62
     suits
    -1.48
     fires
    -1.45
     Fires
    -1.23
    fires
    -1.16
     Suit
    -1.06
     Suits
    -1.02
     earliest
    -0.93
    Suit
    -0.92
    suits
    -0.90
    POSITIVE LOGITS
    ThroughAttribute
    0.69
    Kjelder
    0.63
    NameInMap
    0.63
     Савезне
    0.51
    uminous
    0.49
    ]]:
    0.49
    ')):
    0.49
     ffilm
    0.47
    Erstellt
    0.47
    YSTEM
    0.47
    Act Density 1.114%

    No Known Activations