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

    Neuronpedia

    INDEX
    Explanations

    cheat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aire
    -0.07
    .Appearance
    -0.07
     of
    -0.07
    亸
    -0.07
    ��
    -0.07
    ">↵↵
    -0.07
     Mall
    -0.07
    ㈱
    -0.07
    ">↵
    -0.07
     inn
    -0.06
    POSITIVE LOGITS
     immigrants
    0.08
    ᶜ
    0.07
    比分
    0.07
    �
    0.07
    again
    0.07
     /^\
    0.07
     مواضيع
    0.07
     cheat
    0.07
    呓
    0.07
     orbits
    0.07
    Act Density 0.003%

    No Known Activations