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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    |()
    -0.63
     setuptools
    -0.62
    Extinguishing
    -0.56
    MessageTagHelper
    -0.55
    expandindo
    -0.54
     plots
    -0.54
     figliu
    -0.54
    Хьажоргаш
    -0.54
    oliver
    -0.54
    Abitanti
    -0.53
    POSITIVE LOGITS
    TagMode
    0.61
    BeginContext
    0.49
     ninth
    0.48
     protoimpl
    0.48
    neum
    0.47
    lemény
    0.45
     دهه
    0.44
    thoscope
    0.43
     uintptr
    0.43
    
    0.42
    Act Density 0.002%

    No Known Activations