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

    Neuronpedia

    INDEX
    Explanations

    lack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invokingState
    -0.60
    Geplaatst
    -0.56
     udaler
    -0.51
    Bekijk
    -0.48
     <>",
    -0.45
     contracted
    -0.45
    </caption>
    -0.45
    %)$
    -0.44
     bygget
    -0.44
     Học
    -0.44
    POSITIVE LOGITS
    AccessorTable
    0.64
     يتيمه
    0.64
    (!__
    0.61
    \{\\
    0.55
     nakalista
    0.53
     Picchu
    0.53
     poveznice
    0.53
     tartalomajánló
    0.52
     تانيه
    0.50
    usermodel
    0.50
    Act Density 0.002%

    No Known Activations