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

    Neuronpedia

    INDEX
    Explanations

    acting, portraying a role

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mole
    -0.08
    -sp
    -0.07
     Bel
    -0.06
    (src
    -0.06
     Steven
    -0.06
     Rose
    -0.06
     Niet
    -0.06
     Brew
    -0.06
     Ci
    -0.06
    .limit
    -0.06
    POSITIVE LOGITS
     whatever
    0.07
    ieran
    0.06
     页面
    0.06
    三个
    0.06
    ッ
    0.06
    CLEAR
    0.06
     prevail
    0.06
    Confirmation
    0.06
    \Config
    0.06
    	video
    0.06
    Act Density 0.018%

    No Known Activations