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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getTable
    -0.07
    ups
    -0.07
     mana
    -0.07
    rible
    -0.06
     Pos
    -0.06
     drain
    -0.06
     tipping
    -0.06
     sớm
    -0.06
     rtl
    -0.06
    sequences
    -0.06
    POSITIVE LOGITS
     getBy
    0.06
     Producto
    0.06
    orry
    0.06
     ():
    0.06
    ुपए
    0.06
    [^
    0.06
     SignIn
    0.06
     assists
    0.06
    _THAN
    0.06
     hallmark
    0.06
    Act Density 0.011%

    No Known Activations