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

    Neuronpedia

    INDEX
    Explanations

    technical documentation/code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	input
    -0.07
     Daddy
    -0.07
     stones
    -0.06
    itting
    -0.06
    ofile
    -0.06
     Mama
    -0.06
     استاندارد
    -0.06
    -design
    -0.06
     đọc
    -0.06
    .,
    -0.06
    POSITIVE LOGITS
    ",$
    0.07
    ufact
    0.06
    navbarDropdown
    0.06
     mockMvc
    0.06
     無
    0.06
     precarious
    0.06
    折
    0.06
    のに
    0.06
     removeObject
    0.06
     trải
    0.06
    Act Density 0.023%

    No Known Activations