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

    Neuronpedia

    INDEX
    Explanations

    heavy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    리에
    -0.07
    Pipe
    -0.06
    弄
    -0.06
     blatantly
    -0.06
    WindowState
    -0.06
    Thumb
    -0.06
    Wi
    -0.06
    kla
    -0.06
     gi�
    -0.06
    _have
    -0.06
    POSITIVE LOGITS
     hexadecimal
    0.08
    Sym
    0.06
     immun
    0.06
    алог
    0.06
     Dummy
    0.06
    τική
    0.06
     품
    0.06
     Sunni
    0.06
     美
    0.06
     kron
    0.06
    Act Density 0.000%

    No Known Activations