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

    Neuronpedia

    INDEX
    Explanations

    borrow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    entication
    -0.06
     circuits
    -0.06
    Programming
    -0.06
    Selective
    -0.06
    (TAG
    -0.06
     eleven
    -0.06
    冲
    -0.06
     wl
    -0.06
    ircuit
    -0.06
    unication
    -0.06
    POSITIVE LOGITS
     borrow
    0.08
     borrowed
    0.07
     manpower
    0.07
    basename
    0.06
     changer
    0.06
    не
    0.06
     gereken
    0.06
    нить
    0.06
     used
    0.06
    /theme
    0.06
    Act Density 0.005%

    No Known Activations