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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liked
    -0.08
     caster
    -0.08
    效益
    -0.08
    ood
    -0.07
     Wood
    -0.07
    ält
    -0.07
    EMBER
    -0.07
    anza
    -0.07
    adow
    -0.07
     sắc
    -0.07
    POSITIVE LOGITS
    فن
    0.07
    _categorical
    0.07
    .configureTestingModule
    0.07
    加班
    0.07
     acos
    0.07
    isempty
    0.06
     Mish
    0.06
    𝔰
    0.06
    memberof
    0.06
    .onload
    0.06
    Act Density 1.054%

    No Known Activations