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

    Neuronpedia

    INDEX
    Explanations

    plus or minus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .eng
    -0.07
    פיתוח
    -0.07
    RD
    -0.07
     pursuant
    -0.07
    Dod
    -0.07
     quanto
    -0.07
     conception
    -0.07
     interceptor
    -0.07
    duit
    -0.06
     Infect
    -0.06
    POSITIVE LOGITS
     autobi
    0.08
    抡
    0.07
    .ISupportInitialize
    0.07
     наш
    0.07
    .LinearLayoutManager
    0.07
    镌
    0.07
    .setTimeout
    0.07
    .setIcon
    0.07
    甩
    0.07
     świe
    0.06
    Act Density 0.005%

    No Known Activations