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

    Neuronpedia

    INDEX
    Explanations

    safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getLast
    -0.06
     malfunction
    -0.06
     Leeds
    -0.06
     Aut
    -0.06
    _hand
    -0.06
    으로
    -0.06
     Glenn
    -0.06
    _CL
    -0.06
    PURE
    -0.06
    ,↵↵↵↵
    -0.06
    POSITIVE LOGITS
    .ImageLayout
    0.06
     stud
    0.06
     Seller
    0.06
     zun
    0.06
     مسجد
    0.06
    '):↵
    0.06
     پذیر
    0.06
    (Mouse
    0.06
     iam
    0.06
     hudeb
    0.06
    Act Density 0.044%

    No Known Activations