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

    Neuronpedia

    INDEX
    Explanations

    processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Majefty
    -0.85
     purpoſe
    -0.78
     fevere
    -0.77
     ftate
    -0.75
     ſtate
    -0.75
     chré
    -0.74
    ^(@)
    -0.73
     ſmall
    -0.73
     Monfieur
    -0.72
     fhew
    -0.71
    POSITIVE LOGITS
     for
    0.58
    oredCriteria
    0.55
    ,
    0.50
     (
    0.50
     to
    0.49
    .
    0.49
    GOTREF
    0.49
    ليق
    0.48
     
    0.46
     from
    0.45
    Act Density 0.116%

    No Known Activations