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

    Neuronpedia

    INDEX
    Explanations

    deadpan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Connections
    -0.08
    (depend
    -0.07
     구
    -0.06
    HD
    -0.06
     tong
    -0.06
     Safety
    -0.06
    .TabControl
    -0.06
     represents
    -0.06
     Containers
    -0.06
     connections
    -0.06
    POSITIVE LOGITS
     yüzyıl
    0.07
     ….
    0.07
     dresser
    0.06
    े,
    0.06
    ío
    0.06
    いう
    0.06
    -Co
    0.06
    .stdout
    0.06
     astonished
    0.06
     Ae
    0.06
    Act Density 0.009%

    No Known Activations