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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.83
    antaranya
    -0.81
    Datuak
    -0.81
    horabuena
    -0.79
     bezeichneter
    -0.75
     Мексичка
    -0.74
    ParallelGroup
    -0.73
     فريبيس
    -0.73
     BorderRadius
    -0.73
     poveznice
    -0.73
    POSITIVE LOGITS
     an
    0.75
     a
    0.74
     the
    0.74
     there
    0.65
     needed
    0.60
     left
    0.60
     one
    0.59
     little
    0.58
     not
    0.58
     patients
    0.57
    Act Density 0.067%

    No Known Activations