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

    Neuronpedia

    INDEX
    Explanations

    scientific citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Integral
    -0.07
    ☪
    -0.07
     Flat
    -0.07
    婍
    -0.07
     Decom
    -0.06
    搽
    -0.06
     baptized
    -0.06
     plague
    -0.06
     �
    -0.06
     Insert
    -0.06
    POSITIVE LOGITS
     needles
    0.07
     Dallas
    0.07
     Universität
    0.07
    卒
    0.07
    resolution
    0.07
     vraiment
    0.07
    问答
    0.07
     Mb
    0.06
     jmp
    0.06
     đoàn
    0.06
    Act Density 0.001%

    No Known Activations