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

    Neuronpedia

    INDEX
    Explanations

    problem-solving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    i
    -0.98
    ly
    -0.72
    ed
    -0.71
    y
    -0.71
    sies
    -0.69
    o
    -0.67
    en
    -0.65
    a
    -0.61
    er
    -0.59
    ie
    -0.59
    POSITIVE LOGITS
    DockStyle
    0.98
     myſelf
    0.85
     Jefus
    0.84
    følgelig
    0.84
     itſelf
    0.83
    CloseOperation
    0.83
    ^(@)
    0.81
     Faker
    0.80
     mergeFrom
    0.79
    ſelves
    0.77
    Act Density 0.052%

    No Known Activations