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

    Neuronpedia

    INDEX
    Explanations

    software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     filmy
    -0.07
     Теп
    -0.07
    遇
    -0.06
     fixture
    -0.06
    .Arguments
    -0.06
    ीब
    -0.06
    .exec
    -0.06
    豪
    -0.06
    nět
    -0.06
    ника
    -0.06
    POSITIVE LOGITS
    ++↵
    0.07
    _↵
    0.06
     благ
    0.06
    vé
    0.06
     (!_
    0.06
    …↵↵
    0.06
    Energy
    0.06
    _audit
    0.06
    форт
    0.06
    óst
    0.06
    Act Density 0.050%

    No Known Activations