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

    Neuronpedia

    INDEX
    Explanations

    Microsoft software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reload
    -0.07
    ηγ
    -0.06
     около
    -0.06
    -at
    -0.06
    infeld
    -0.06
     relentless
    -0.06
     Reno
    -0.06
     있고
    -0.06
    FlowLayout
    -0.06
    站在
    -0.06
    POSITIVE LOGITS
    AuthGuard
    0.06
    (curl
    0.06
    _word
    0.06
    consulta
    0.06
    ponce
    0.06
    :".$
    0.06
    .boost
    0.06
    (rot
    0.06
    (instruction
    0.06
    usi
    0.06
    Act Density 0.021%

    No Known Activations