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

    Neuronpedia

    INDEX
    Explanations

    avoid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.80
    ſelf
    -0.77
     Monfieur
    -0.76
     Efq
    -0.73
     photolibrary
    -0.72
     becauſe
    -0.71
     становника
    -0.69
     Houſe
    -0.66
     Majefty
    -0.66
     raiſ
    -0.64
    POSITIVE LOGITS
     hear
    0.54
     supérieurs
    0.52
    équi
    0.51
     declare
    0.50
     trị
    0.50
     quantités
    0.49
     schaffen
    0.49
     OnInit
    0.47
     traités
    0.47
     peines
    0.46
    Act Density 0.057%

    No Known Activations