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

    Neuronpedia

    INDEX
    Explanations

    cognitive psychology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Button
    -0.08
     (
    -0.07
    .Background
    -0.07
     Wetter
    -0.07
     Nicholas
    -0.07
     Morris
    -0.07
     background
    -0.07
    INSERT
    -0.07
     Insert
    -0.07
    Background
    -0.07
    POSITIVE LOGITS
    !”,
    0.09
     resend
    0.09
    forgot
    0.08
     직
    0.08
    คืน
    0.08
     없
    0.08
    !!!!!↵↵
    0.08
     ไม่มี
    0.08
     forgotten
    0.08
     resurrection
    0.08
    Act Density 0.001%

    No Known Activations