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

    Neuronpedia

    INDEX
    Explanations

    Code snippets/API responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    ij
    -0.07
     women
    -0.06
     markers
    -0.06
     chicken
    -0.06
    Encrypt
    -0.06
    .Course
    -0.06
    theid
    -0.06
     mpi
    -0.06
    Invalid
    -0.06
    POSITIVE LOGITS
    @Autowired
    0.08
    _MISS
    0.08
     moderated
    0.06
    batis
    0.06
    (ds
    0.06
     Québec
    0.06
    óln
    0.06
     Jets
    0.06
    ویس
    0.06
     definitely
    0.06
    Act Density 0.223%

    No Known Activations