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

    Neuronpedia

    INDEX
    Explanations

    sitting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    God
    -0.07
    费用
    -0.07
    推動
    -0.07
    (tmp
    -0.07
    別
    -0.07
     Was
    -0.07
     بما
    -0.07
    ering
    -0.07
    gement
    -0.07
     workshop
    -0.07
    POSITIVE LOGITS
     nightlife
    0.08
    .Conn
    0.08
    ⺠
    0.07
     Lik
    0.07
    -connect
    0.07
     рег
    0.07
     firefight
    0.07
     encounters
    0.07
     Hashtable
    0.07
    霾
    0.07
    Act Density 0.001%

    No Known Activations