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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    جان
    -0.07
    uggest
    -0.07
    merican
    -0.07
     criar
    -0.07
    ด
    -0.06
    chází
    -0.06
    불
    -0.06
     Kid
    -0.06
     violates
    -0.06
    VR
    -0.06
    POSITIVE LOGITS
     juven
    0.07
    uridad
    0.06
     scrutin
    0.06
     wifi
    0.06
     uploads
    0.06
    .EntityFrameworkCore
    0.06
     signup
    0.06
     <![
    0.06
    _succ
    0.06
     Transition
    0.06
    Act Density 0.032%

    No Known Activations