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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Passenger
    -0.07
    -policy
    -0.06
    php
    -0.06
     "$
    -0.06
    picker
    -0.06
    copies
    -0.06
    приєм
    -0.06
     cánh
    -0.06
    _board
    -0.06
    (nt
    -0.06
    POSITIVE LOGITS
     직
    0.07
    Walk
    0.07
     CHK
    0.06
    ่าม
    0.06
    _recursive
    0.06
    earer
    0.06
    _scalar
    0.06
    .Apis
    0.06
    ců
    0.06
    oppins
    0.06
    Act Density 0.045%

    No Known Activations