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

    Neuronpedia

    INDEX
    Explanations

    binds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.81
     binds
    -0.67
    SequentialGroup
    -0.57
    rdom
    -0.54
    tymologie
    -0.51
    patreon
    -0.50
    ribadian
    -0.50
    eability
    -0.50
    شنایی
    -0.49
     AssemblyCompany
    -0.49
    POSITIVE LOGITS
     itſelf
    1.02
     myſelf
    0.93
     Monfieur
    0.92
     Anſ
    0.88
     purpoſe
    0.87
     greateſt
    0.87
     themſelves
    0.86
     becauſe
    0.85
     pleaſure
    0.85
     poffe
    0.83
    Act Density 0.065%

    No Known Activations