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

    Neuronpedia

    INDEX
    Explanations

    LaTeX code, math notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    teil
    -0.07
     Veterans
    -0.07
    ⇤
    -0.07
     humili
    -0.07
     network
    -0.06
     Wonder
    -0.06
     logistic
    -0.06
    tank
    -0.06
     mus
    -0.06
     bur
    -0.06
    POSITIVE LOGITS
     dõi
    0.07
    훔
    0.07
     Roof
    0.07
    gether
    0.07
     السم
    0.07
    כים
    0.07
    Manifest
    0.07
    :red
    0.06
     ром
    0.06
    货币政策
    0.06
    Act Density 0.025%

    No Known Activations