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

    Neuronpedia

    INDEX
    Explanations

    approach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doubtnut
    -0.87
     itſelf
    -0.85
     faſt
    -0.77
     purpoſe
    -0.76
     myſelf
    -0.75
     pleaſure
    -0.75
     approche
    -0.73
     سكانية
    -0.73
    ſelves
    -0.71
     himſelf
    -0.70
    POSITIVE LOGITS
     a
    0.67
     an
    0.56
     p
    0.53
    GEBURTSDATUM
    0.52
    defineProperty
    0.52
     any
    0.52
     life
    0.50
     des
    0.50
     je
    0.50
     having
    0.50
    Act Density 0.007%

    No Known Activations