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

    Neuronpedia

    INDEX
    Explanations

    plans and attempts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chain
    -1.03
     Chain
    -0.96
     CHAIN
    -0.85
    Chain
    -0.77
    Plan
    -0.75
     Plan
    -0.70
     chains
    -0.68
     chaine
    -0.67
     تضيفلها
    -0.65
    CHAIN
    -0.63
    POSITIVE LOGITS
    tualmente
    0.51
    Dés
    0.50
    ners
    0.48
     propOrder
    0.48
     Theſe
    0.47
    toplankton
    0.47
     ſeveral
    0.46
     Monfieur
    0.46
    geord
    0.46
    paravant
    0.46
    Act Density 1.277%

    No Known Activations