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

    Neuronpedia

    INDEX
    Explanations

    events, lectures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    胡
    -0.06
     homers
    -0.06
    道路
    -0.06
     XSS
    -0.06
    rates
    -0.06
    侯
    -0.06
    랜드
    -0.06
    AILS
    -0.06
     lö
    -0.06
    /vnd
    -0.06
    POSITIVE LOGITS
     goodwill
    0.07
     ณ
    0.07
    Rightarrow
    0.06
    punkt
    0.06
    102
    0.06
    ,unsigned
    0.06
    ат
    0.06
     ingress
    0.06
     Cooling
    0.06
     scanner
    0.06
    Act Density 0.016%

    No Known Activations