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

    Neuronpedia

    INDEX
    Explanations

    foreign language fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IVED
    -0.07
    
    -0.06
     interviews
    -0.06
     ↵ ↵
    -0.06
    ensive
    -0.06
    times
    -0.06
    ратег
    -0.06
    struction
    -0.06
     Shea
    -0.06
     rifle
    -0.06
    POSITIVE LOGITS
    (State
    0.06
     subpo
    0.06
    England
    0.06
    ็นผ
    0.06
     fiat
    0.06
     migli
    0.06
    (ac
    0.06
     τις
    0.06
     ae
    0.06
    ONY
    0.06
    Act Density 0.050%

    No Known Activations