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

    Neuronpedia

    INDEX
    Explanations

    scientific abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raises
    -0.07
    ların
    -0.07
     partir
    -0.07
    恐
    -0.07
     Principal
    -0.07
     bizim
    -0.07
    BeforeEach
    -0.06
     mosques
    -0.06
    .Some
    -0.06
     humano
    -0.06
    POSITIVE LOGITS
    ="<?
    0.07
    ============↵
    0.06
     Jess
    0.06
    asaki
    0.06
    alking
    0.06
      ↵  ↵
    0.06
    flo
    0.06
    處
    0.06
    _holder
    0.06
    -sizing
    0.05
    Act Density 0.027%

    No Known Activations